Search

Previous studies were mostly conducted based on sparse time series and different phenological images, which often ignored the dramatic changes in salinization evolution throughout the year. Based on Landsat and moderate-resolution-imaging spectroradiometer (MODIS) images from 2000 to 2020, this study applied the Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM) algorithm to obtain similar phenological images for the month of April for the past 20 years. Based on the random forest algorithm, the surface parameters of the salinization were optimized, and the feature space index models were constructed. Combined with the measured ground data, the optimal monitoring index model of salinization was determined, and then the spatiotemporal evolution patterns of salinization and its driving mechanisms in the Yellow River Delta were revealed. The main conclusions were as follows: (1) The derived long-time-series and similar phenological-fusion images enable us to reveal the patterns of change in the dramatic salinization in the year that we examined using the ESTARFM algorithm. (2) The NDSI-TGDVI feature space salinization monitoring index model based on point-to-point mode had the highest accuracy of 0.92. (3) From 2000 to 2020, the soil salinization in the Yellow River Delta showed an aggravating trend. The average value of salinization during the past 20 years was 0.65, which is categorized as severe salinization. The degree of salinization gradually decreased from the northeastern coastal area to the southwestern inland area. (4) The dominant factors affecting soil salinization in different historical periods varied. The research results could provide support for decision-making regarding the precise prevention and control of salinization in the Yellow River Delta. [ABSTRACT FROM AUTHOR]

Tree species classification using hyperspectral imagery shows incredible promise in developing a large-scale, high-resolution model for identifying tree species, providing unprecedented details on global tree species distribution. Many questions remain unanswered about the best practices for creating a global, general hyperspectral tree species classification model. This study aims to address three key issues in creating a hyperspectral species classification model. We assessed the effectiveness of three data-labeling methods to create training data, three data-splitting methods for training/validation/testing, and machine-learning and deep-learning (including semi-supervised deep-learning) models for tree species classification using hyperspectral imagery at National Ecological Observatory Network (NEON) Sites. Our analysis revealed that the existing data-labeling method using the field vegetation structure survey performed reasonably well. The random tree data-splitting technique was the most efficient method for both intra-site and inter-site classifications to overcome the impact of spatial autocorrelation to avoid the potential to create a locally overfit model. Deep learning consistently outperformed random forest classification; both semi-supervised and supervised deep-learning models displayed the most promising results in creating a general taxa-classification model. This work has demonstrated the possibility of developing tree-classification models that can identify tree species from outside their training area and that semi-supervised deep learning may potentially utilize the untapped terabytes of unlabeled forest imagery. [ABSTRACT FROM AUTHOR]

Soil nutrient content varies spatially across agricultural fields in hard-to-predict ways, particularly in floodplains with complex fluvial depositional history. Satellite reflectance data from the Sentinel-2 (S2) mission provides spatially continuous land reflectance data that can aid model development when used with point observations of nutrients. Reflectance from vegetation is assumed to obstruct land reflectance of bare soil, such that researchers have masked vegetation in models. We developed a routine for masking vegetation within Google Earth Engine (GEE) using Random Forest classification for iterative application to libraries of S2-images. Using gradient boosting, we then developed soil nutrient models for surface soils at a 250-ha agricultural site using S2 images. Soils were sampled at 2145 point locations to a 23-cm depth and analyzed for Ca, K, Mg, P, pH, S, and Zn. Results showed that masking vegetation improved model performance for models from subsets of the data (80% of samples used for model development, 20% validation), but full data sets did not require masking to achieve accuracy. Models of Ca, K, Mg, and S were successful (validation R2 > 0.60 to 0.96), but models for pH, P, and Zn failed. Bare soil composite images from S2 data are helpful in predicting soil fertility in low-relief floodplains. [ABSTRACT FROM AUTHOR]

Accurate prediction of lake surface water temperature (LSWT) is essential for understanding the impacts of climate change on aquatic ecosystems and for guiding environmental management strategies. Predictions of LSWT for two prominent lakes in northern China, Qinghai Lake and Hulun Lake, under various future climate scenarios, were conducted in the present study. Utilizing historical hydrometeorological data and MODIS satellite observations (MOD11A2), we employed three advanced machine learning models—Random Forest (RF), XGBoost, and Multilayer Perceptron Neural Network (MLPNN)—to predict monthly average LSWT across three future climate scenarios (ssp119, ssp245, ssp585) from CMIP6 projections. Through the comparison of training and validation results of the three models across both lake regions, the RF model demonstrated the highest accuracy, with a mean MAE of 0.348 °C and an RMSE of 0.611 °C, making it the most optimal and suitable model for this purpose. With this model, the predicted LSWT for both lakes reveals a significant warming trend in the future, particularly under the high-emission scenario (ssp585). The rate of increase is most pronounced under ssp585, with Hulun Lake showing a rise of 0.55 °C per decade (R2 = 0.72) and Qinghai Lake 0.32 °C per decade (R2 = 0.85), surpassing trends observed under ssp119 and ssp245. These results underscore the vulnerability of lake ecosystems to future climate change and provide essential insights for proactive climate adaptation and environmental management. [ABSTRACT FROM AUTHOR]

Accurate river ice mapping is crucial for predicting and managing floods caused by ice jams and for the safe operation of hydropower and water resource facilities. Although satellite multispectral images are widely used for river ice mapping, atmospheric contamination limits their effectiveness. This study developed river ice mapping models for the Han River in South Korea using atmospherically uncorrected Landsat-8 Operational Land Imager (OLI) multispectral reflectance data, addressing atmospheric influences with a Random Forest (RF) classification approach. The RF-based river ice mapping models were developed by implementing various combinations of input variables, incorporating the Landsat-8 multispectral top-of-atmosphere (TOA) reflectance, normalized difference indices for snow, water, and bare ice, and atmospheric factors such as aerosol optical depth, water vapor content, and ozone concentration from the Moderate Resolution Imaging Spectroradiometer observations, as well as surface elevation from the GLO-30 digital elevation model. The RF model developed using all variables achieved excellent performance in the classification of snow-covered ice, snow-free ice, and water, with an overall accuracy and kappa coefficient exceeding 98.4% and 0.98 for test samples, and higher than 83.7% and 0.75 when compared against reference river ice maps generated by manually interpreting the Landsat-8 images under various atmospheric conditions. The RF-based river ice mapping model for the atmospherically corrected Landsat-8 multispectral surface reflectance was also developed, but it showed very low performance under atmospheric conditions heavily contaminated by aerosol and water vapor. Aerosol optical depth and water vapor content were identified as the most important variables. This study demonstrates that multispectral reflectance data, despite atmospheric contamination, can be effectively used for river ice monitoring by applying machine learning with atmospheric auxiliary data to mitigate atmospheric effects. [ABSTRACT FROM AUTHOR]

Determining the responses of non-photosynthetic vegetation (NPV) and photosynthetic vegetation (PV) communities to climate change is crucial in illustrating the sensitivity and sustainability of these ecosystems. In this study, we evaluated the accuracy of inverting NPV and PV using Landsat imagery with random forest (RF), backpropagation neural network (BPNN), and fully connected neural network (FCNN) models. Additionally, we inverted MODIS NPV and PV time-series data using spectral unmixing. Based on this, we analyzed the responses of NPV and PV to precipitation and drought across different ecological regions. The main conclusions are as follows: (1) In NPV remote sensing inversion, the softmax activation function demonstrates greater advantages over the ReLU activation function. Specifically, the use of the softmax function results in an approximate increase of 0.35 in the R2 value. (2) Compared with a five-layer FCNN with 128 neurons and a three-layer BPNN with 12 neurons, a random forest model with over 50 trees and 5 leaf nodes provides better inversion results for NPV and PV (R2_RF-NPV = 0.843, R2_RF-PV = 0.861). (3) Long-term drought or heavy rainfall events can affect the utilization of precipitation by NPV and PV. There is a high correlation between extreme precipitation events following prolonged drought and an increase in PV coverage. (4) Under long-term drought conditions, the vegetation in the study area responded to precipitation during the last winter and growing season. This study provides an illustration of the response of semi-arid ecosystems to drought and wetting events, thereby offering a data basis for the effect evaluation of afforestation projects. [ABSTRACT FROM AUTHOR]

Global warming and climate change are significantly impacting local climates, causing more intense heat during the summer season, which poses risks to individuals with pre-existing health conditions and negatively affects overall human health. While various studies have examined the Surface Urban Heat Island (SUHI) phenomenon, these studies often focus on small to large geographic regions using low-to-moderate-resolution data, highlighting general thermal trends across large administrative areas. However, there is a growing need for methods that can detect microscale thermal patterns in environments familiar to urban residents, such as streets and alleys. The temperature-humidity index (THI), which incorporates both temperature and humidity data, serves as a critical measure of human-perceived heat. However, few studies have explored microscale THI variations within urban settings and identified potential THI hotspots at a local level where SUHI effects are pronounced. This research aims to address this gap by estimating THI at a finer resolution scale using data from multiple sensor platforms. We developed a model with the random forest algorithm to assess THI trends at a resolution of 0.5 m, utilizing various variables from different sources, including Landsat 8 land surface temperature (LST), unmanned aerial system (UAS)-derived LST, Sentinel-2 NDVI and NDMI, a wind exposure index, solar radiation modeled from aircraft and UAS-derived Digital Surface Models, and vehicle density and building floor area from social big data. Two models were constructed with different variables: Modelnatural, which includes variables related to only natural factors, and Modelmix, which includes all variables, including anthropogenic factors. The two models were compared to reveal how each source contributes to the model development and SUHI effects. The results show significant improvements, as Modelnatural had a fitting R2 = 0.5846, a root mean square error (RMSE) = 0.5936 and a mean absolute error (MAE) = 0.4294. Moreover, when anthropogenic factors were introduced, Modelmix performed even better, with R2 = 0.9638, RMSE = 0.1751, and MAE = 0.1065 (n = 923). This study contributes to the future of microscale SUHI analysis and offers important insights into urban planning and smart city development. [ABSTRACT FROM AUTHOR]

Detecting clouds, snow, and lakes in remote sensing images is vital due to their propensity to obscure underlying surface information and hinder data extraction. In this study, we utilize Sentinel-2 images to implement a two-stage random forest (RF) algorithm for image labeling and delve into the factors influencing neural network performance across six aspects: model architecture, encoder, learning rate adjustment strategy, loss function, input image size, and different band combinations. Our findings indicate the Feature Pyramid Network (FPN) achieved the highest MIoU of 87.14%. The multi-head self-attention mechanism was less effective compared to convolutional methods for feature extraction with small datasets. Incorporating residual connections into convolutional blocks notably enhanced performance. Additionally, employing false-color images (bands 12-3-2) yielded a 4.86% improvement in MIoU compared to true-color images (bands 4-3-2). Notably, variations in model architecture, encoder structure, and input band combination had a substantial impact on performance, with parameter variations resulting in MIoU differences exceeding 5%. These results provide a reference for high-precision segmentation of clouds, snow, and lakes and offer valuable insights for applying deep learning techniques to the high-precision extraction of information from remote sensing images, thereby advancing research in deep neural networks for semantic segmentation. [ABSTRACT FROM AUTHOR]

LiDAR-unmanned aerial system (LiDAR-UAS) technology can accurately and efficiently obtain detailed and accurate three-dimensional spatial information of objects. The classification of objects in estuarine areas is highly important for management, planning, and ecosystem protection. Owing to the presence of slopes in estuarine areas, distinguishing between dense vegetation (lawns and trees) on slopes and the ground at the tops of slopes is difficult. In addition, the imbalance in the number of point clouds also poses a challenge for accurate classification directly from point cloud data. A multifeature-assisted and multilayer fused neural network (MLF-PointNet++) is proposed for LiDAR-UAS point cloud classification in estuarine areas. First, the 3D shape features that characterize the geometric characteristics of targets and the visible-band difference vegetation index (VDVI) that can characterize vegetation distribution are used as auxiliary features to enhance the distinguishability of dense vegetation (lawns and trees) on slopes and the ground at the tops of slopes. Second, to enhance the extraction of target spatial information and contextual relationships, the feature vectors output by different layers of set abstraction in the PointNet++ model are fused to form a combined feature vector that integrates low and high-level information. Finally, the focal loss function is adopted as the loss function in the MLF-PointNet++ model to reduce the effect of imbalance in the number of point clouds in each category on the classification accuracy. A classification evaluation was conducted using LiDAR-UAS data from the Moshui River estuarine area in Qingdao, China. The experimental results revealed that MLF-PointNet++ had an overall accuracy (OA), mean intersection over union (mIOU), kappa coefficient, precision, recall, and F1-score of 0.976, 0.913, 0.960, 0.953, 0.953, and 0.953, respectively, for object classification in the three representative areas, which were better than the corresponding values for the classification methods of random forest, BP neural network, Naive Bayes, PointNet, PointNet++, and RandLA-Net. The study results provide effective methodological support for the classification of objects in estuarine areas and offer a scientific basis for the sustainable development of these areas. [ABSTRACT FROM AUTHOR]

Machine learning methods have improved in recent years and provide increasingly powerful tools for understanding landscape evolution. In this study, we used the random forest method based on Google Earth Engine to evaluate the desertification dynamics in northern China from 1995 to 2020. We selected Landsat series image bands, remote sensing inversion data, climate baseline data, land use data, and soil type data as variables for majority voting in the random forest method. The method's average classification accuracy was 91.6% ± 5.8 [mean ± SD], and the average kappa coefficient was 0.68 ± 0.09, suggesting good classification results. The random forest classifier results were consistent with the results of visual interpretation for the spatial distribution of different levels of desertification. From 1995 to 2000, the area of aeolian desertification increased at an average rate of 9977 km2 yr−1, and from 2000 to 2005, from 2005 to 2010, from 2010 to 2015, and from 2015 to 2020, the aeolian desertification decreased at an average rate of 2535, 3462, 1487, and 4537 km2 yr−1, respectively. [ABSTRACT FROM AUTHOR]

Leaf area index (LAI) is a key variable for monitoring crop growth. Compared with traditional measurement methods, unmanned aerial vehicle (UAV) remote sensing offers a cost-effective and efficient approach for rapidly obtaining crop LAI. Although there is extensive research on rice LAI estimation, many studies suffer from the limitations of models that are only applicable to specific scenarios with unclear applicability conditions. In this study, we selected commonly used RGB and multispectral (Ms) data sources, which contain three channels of color information and five multi-band information, respectively, combined with five different spatial resolutions of data at intervals of 20–100 m. We evaluated the effectiveness of models using single- and multi-feature variables for LAI estimation in rice. In addition, texture and coverage features other than spectra were introduced to further analyze their effects on the inversion accuracy of the LAI. The results show that the accuracy of the model established with multi-variables under single features is significantly higher than that of the model established with single variables under single features. The best results were obtained using the RFR (random forest regression) model, in which the model's R2 is 0.675 and RMSE is 0.886 for multi-feature VIs at 40 m. Compared with the analysis results of Ms and RGB data at different heights, the accuracy of Ms data estimation results fluctuates slightly and is less sensitive to spatial resolution, while the accuracy of the results based on RGB data gradually decreases with the increase in height. The estimation accuracies of both Ms and RGB data were improved by adding texture features and coverage features, and their R2 improved by 9.1% and 7.3% on average. The best estimation heights (spatial resolution) of the two data sources were 40 m (2.2 cm) and 20 m (0.4 cm), with R2 of 0.724 and 0.673, and RMSE of 0.810 and 0.881. This study provides an important reference for the estimation of rice LAI based on RGB and Ms data acquired using the UAV platform. [ABSTRACT FROM AUTHOR]

Soil erodibility (K) refers to the inherent ability of soil to withstand erosion. Accurate estimation and spatial prediction of K values are vital for assessing soil erosion and managing land resources. However, as most K-value estimation models are empirical, they suffer from significant extrapolation uncertainty, and traditional studies on spatial prediction focusing on individual empirical K values have neglected to explore the spatial pattern differences between various empirical models. This work proposed a universal framework for selecting an optimal soil-erodibility map using empirical models enhanced by machine learning. Specifically, three empirical models, namely, the erosion-productivity impact calculator model (K_EPIC), the Shirazi model (K_Shirazi), and the Torri model (K_Torri) were used to estimate K values. Random Forest (RF) and Gradient-Boosting Decision Tree (GBDT) algorithms were employed to develop prediction models, which led to the creation of three K-value maps. The spatial distribution of K values and associated environmental covariates were also investigated across varying empirical models. Results showed that RF achieved the highest accuracy, with R2 of K_EPIC, K_Shirazi, and K_Torri increasing by 46%, 34%, and 22%, respectively, compared to GBDT. And distinctions among environmental variables that shape the spatial patterns of empirical models have been identified. The K_EPIC and K_Shirazi are influenced by soil porosity and soil moisture. The K_Torri is more sensitive to soil moisture conditions and terrain location. More importantly, our study has highlighted disparities in the spatial patterns across the three K-value maps. Considering the data distribution, spatial distribution, and measured K values, the K_Torri model outperformed others in estimating soil erodibility in the plateau lake watershed. This study proposed a framework that aimed to create optimal soil-erodibility maps and offered a scientific and accurate K-value estimation method for the assessment of soil erosion. [ABSTRACT FROM AUTHOR]

The ocean tide loading (OTL) can result in displacements of centimeters or even decimeters at nearshore stations. Global ocean tide models exhibit errors in nearshore regions, which limit the accuracy of maintaining the coordinates of these stations. GNSS positioning can obtain tidal load displacements in nearshore areas, but it often requires long-term observation data and cannot provide timely correction models for newly established reference stations. This paper proposes a method for an empirical correction model of short-term OTL displacements using GNSS observations, where the kinematic coordinate sequences are first obtained by multi-GNSS precise point positioning with ambiguity resolution (PPP-AR), and then the OTL corrections are obtained by window-sliding forecast based on random forest modeling. Through experiments conducted in the Hong Kong region, the empirical model with a window of 15 days is established by the proposed method. After applying the empirical model, root mean square errors of the residuals are reduced by 1.5 (30.6%), 3.7 (53.6%), and 3.7 mm (37.8%) in the East, North, and Up (ENU) components, respectively. When using the global ocean tide model FES2014, the RMSE values are reduced by 1.2 (24.5%), 0.3 (4.3%), and 3.7 mm (37.8%) in the ENU components, respectively. The empirical model shows better effects for the OTL displacement compared to FES2014, especially in the N component, with an improvement ratio of about 49.3%. [ABSTRACT FROM AUTHOR]

High-resolution and accurate precipitation data are essential for hydrological, meteorological, and ecological research at the watershed scale. However, in regions with complex terrain and significant rainfall variability, the limited number of rain gauge stations (RGS) is insufficient, and the spatial resolution of existing satellite precipitation data is too low to capture detailed precipitation patterns at the watershed scale. To address this issue, the downscaling of satellite precipitation products has become an effective method to obtain high-resolution precipitation data. This study proposes a monthly downscaling method based on a random forest model, aiming to improve the resolution of precipitation data in cloudy and rainy regions at mid-to-low latitudes. We combined the Google Earth Engine (GEE) platform with a local Python environment, introducing cloud cover characteristics into traditional downscaling variables (latitude, longitude, topography, and vegetation index). The TRMM data were downscaled from 25 km to 1 km, generating high-resolution monthly precipitation data for the Dongting Lake Basin from 2001 to 2019. Furthermore, we analyzed the spatiotemporal variation characteristics of precipitation in the study area. The results show the following: (1) In cloudy and rainy regions, our method improves resolution and detail while maintaining the accuracy of precipitation data; (2) The response of monthly precipitation to environmental variables varies, with cloud cover characteristics contributing more to the downscaling model than vegetation characteristics, helping to overcome the lag effect of vegetation characteristics; and (3) Over the past 20 years, there have been significant seasonal trends in precipitation changes in the study area, with a decreasing trend in winter and spring (January–May) and an increasing trend in summer and autumn (June–December). These results indicate that the proposed method is suitable for downscaling monthly precipitation data in cloudy and rainy regions of the Dongting Lake Basin. [ABSTRACT FROM AUTHOR]

This paper focuses on large-scale landslide susceptibility modelling in NW Croatia. The objective of this research was to provide new insight into stable and unstable area sampling strategies on a representative inventory of small and shallow landslides mainly occurring in soil and soft rock. Four strategies were tested for stable area sampling (random points, stable area polygon, stable polygon buffering and stable area centroid) in combination with four strategies for unstable area sampling (landslide polygon, smoothing digital terrain model derived landslide conditioning factors, polygon buffering and landslide centroid), resulting in eight sampling scenarios. Using Logistic Regression, Neural Network, Random Forest and Support Vector Machine algorithm, 32 models were derived and analysed. The main conclusions reveal that polygon sampling of unstable areas is an imperative in large-scale modelling, as well as that subjective and/or biased stable area sampling leads to misleading models. Moreover, Random Forest and Neural Network proved to be more favourable methods (0.804 and 0.805 AUC, respectively), but also showed extreme sensitivity to the tested sampling strategies. In the comprehensive comparison, the advantages and disadvantages of 32 derived models were analysed through quantitative and qualitative parameters to highlight their application to large-scale landslide zonation. The results yielded by this research are beneficial to the susceptibility modelling step in large-scale landslide susceptibility assessments as they enable the derivation of more reliable zonation maps applicable to spatial and urban planning systems. [ABSTRACT FROM AUTHOR]

Brazil, a leading rice producer globally, faces challenges in systematically mapping its diverse rice fields due to varying cropping systems, climates, and planting calendars. Existing rice mapping methods often rely on complex techniques like deep learning or microwave imagery, posing limitations for large-scale mapping. This study proposes a novel approach utilizing Sentinel-2 spectral–temporal metrics (STMs) in conjunction with a random forest classifier for rice paddy mapping. By extracting diverse STMs and training both regional and global classifiers, we validated the method across independent areas. While regional models tended to overestimate rice areas, the global model effectively reduced discrepancies between our data and the reference maps, achieving an overall classifier accuracy exceeding 80%. Despite the need for further refinement to address confusion with other crops, STM exhibits promise for national-scale rice paddy mapping in Brazil. [ABSTRACT FROM AUTHOR]

Monitoring air pollution is important for human health and the environment. Previous studies on the prediction of air pollutants from satellite images have employed machine learning, yet there are few enhancements to the constructure of model. Moreover, the existing models have been successful in predicting pollutants like PM2.5, PM10, and O3. They have not been as effective in predicting other primary air pollutants. To improve the overall prediction performance of the existing model, a novel residual learning backpropagation model, abs. as BresNet, has been proposed in this research. This model has revealed the availability to precisely predict the ground-surface concentration of the six primary air pollutants, PM2.5, PM10, O3, NO2, CO, and SO2, based on the satellite imagery of MODIS AOD. Two of the most commonly used machine learning models so far, viz. the multilayer backpropagation neural network (MLBPN) and random forest (RF), were employed as the control. In the conducted experiments, the proposed BresNet model demonstrated significant improvements of 18.75%/31.94%, 33.82%/85.71%, 15.00%/35.29%, 39.06%/134.21%, 23.23%/68.00%, and 137.14%/260.87% in terms of R2 for the six primary air pollutants, compared to the RF/MLBPN model. Moreover, the convergence speed and loss function of the BresNet model compared to that of the MLBPN decreased by 55.15%, revealing superior convergence speed with the lower loss function. [ABSTRACT FROM AUTHOR]

Solar-induced chlorophyll fluorescence (SIF) has been widely utilized to track the dynamics of gross primary productivity (GPP). It has been shown that the photochemical reflectance index (PRI), which may be utilized as an indicator of non-photochemical quenching (NPQ), improves SIF-based GPP estimation. However, the influence of weather conditions on GPP estimation using SIF and PRI has not been well explored. In this study, using an open-access dataset, we examined the impact of the clearness index (CI), which is associated with the proportional intensity of solar incident radiation and can represent weather conditions, on soybean GPP estimation using SIF and PRI. The midday PRI (xanthophyll de-epoxidation state) minus the early morning PRI (xanthophyll epoxidation state) yielded the corrected PRI (ΔPRI), which described the amplitude of xanthophyll pigment interconversion during the day. The observed canopy SIF at 760 nm ( S I F T O C _ 760 ) was downscaled to the broadband photosystem-level SIF for photosystem II ( S I F T O T _ F U L L _ P S I I ). Our results show that GPP can be accurately estimated using a multi-linear model with S I F T O T _ F U L L _ P S I I and ΔPRI. The ratio of GPP measured using the eddy covariance (EC) method ( G P P E C ) to GPP estimated using S I F T O T _ F U L L _ P S I I and ΔPRI exhibited a non-linear correlation with the CI along both the half-hourly (R2 = 0.21) and daily scales (R2 = 0.25). The GPP estimates using S I F T O T _ F U L L _ P S I I and ΔPRI were significantly improved by the addition of the CI (for the half-hourly data, R2 improved from 0.64 to 0.71 and the RMSE decreased from 8.28 to 7.42 μ mol•m−2•s−1; for the daily data, R2 improved from 0.71 to 0.81 and the RMSE decreased from 6.69 to 5.34 μ mol•m−2•s−1). This was confirmed by the validation results. In addition, the GPP estimated using the Random Forest method was also largely improved by considering the influences of the CI. Therefore, our findings demonstrate that GPP can be well estimated using S I F T O T _ F U L L _ P S I I and ΔPRI, and it can be significantly enhanced by accounting for the CI. These results will be beneficial to vegetation GPP estimation using different remote sensing platforms, especially under various weather conditions. [ABSTRACT FROM AUTHOR]

Landslide susceptibility mapping (LSM) can accurately estimate the location and probability of landslides. An effective approach for precise LSM is crucial for minimizing casualties and damage. The existing LSM methods primarily rely on static indicators, such as geomorphology and hydrology, which are closely associated with geo-environmental conditions. However, landslide hazards are often characterized by significant surface deformation. The Small Baseline Subset-Interferometric Synthetic Aperture Radar (SBAS-InSAR) technology plays a pivotal role in detecting and characterizing surface deformation. This work endeavors to assess the accuracy of SBAS-InSAR coupled with ensemble learning for LSM. Within this research, the study area was Shiyan City, and 12 static evaluation factors were selected as input variables for the ensemble learning models to compute landslide susceptibility. The Random Forest (RF) model demonstrates superior accuracy compared to other ensemble learning models, including eXtreme Gradient Boosting, Logistic Regression, Gradient Boosting Decision Tree, and K-Nearest Neighbor. Furthermore, SBAS-InSAR was utilized to obtain surface deformation rates both in the vertical direction and along the line of sight of the satellite. The former is used as a dynamic characteristic factor, while the latter is combined with the evaluation results of the RF model to create a landslide susceptibility optimization matrix. Comparing the precision of two methods for refining LSM results, it was found that the method integrating static and dynamic factors produced a more rational and accurate landslide susceptibility map. [ABSTRACT FROM AUTHOR]

To optimize growth and management, precision agriculture relies on a deep understanding of agricultural dynamics, particularly crop water status analysis. Leveraging unmanned aerial vehicles, we can efficiently acquire high-resolution spatiotemporal samples by utilizing remote sensors. However, non-linear relationships among data features, localized within specific subgroups, frequently emerge in agricultural data. Interpreting these complex patterns requires sophisticated analysis due to the presence of noise, high variability, and non-stationarity behavior in the collected samples. Here, we introduce Local Biplot, a methodological framework tailored for discerning meaningful data patterns in non-stationary contexts for precision agriculture. Local Biplot relies on the well-known uniform manifold approximation and projection method, such as UMAP, and local affine transformations to codify non-stationary and non-linear data patterns while maintaining interpretability. This lets us find important clusters for transformation and projection within a single global axis pair. Hence, our framework encompasses variable and observational contributions within individual clusters. At the same time, we provide a relevance analysis strategy to help explain why those clusters exist, facilitating the understanding of data dynamics while favoring interpretability. We demonstrated our method's capabilities through experiments on both synthetic and real-world datasets, covering scenarios involving grass and rice crops. Moreover, we use random forest and linear regression models to predict water status variables from our Local Biplot-based feature ranking and clusters. Our findings revealed enhanced clustering and prediction capability while emphasizing the importance of input features in precision agriculture. As a result, Local Biplot is a useful tool to visualize, analyze, and compare the intricate underlying patterns and internal structures of complex agricultural datasets. [ABSTRACT FROM AUTHOR]

Wildfire susceptibility maps play a crucial role in preemptively identifying regions at risk of future fires and informing decisions related to wildfire management, thereby aiding in mitigating the risks and potential damage posed by wildfires. This study employs eXplainable Artificial Intelligence (XAI) techniques, particularly SHapley Additive exPlanations (SHAP), to map wildfire susceptibility in Izmir Province, Türkiye. Incorporating fifteen conditioning factors spanning topography, climate, anthropogenic influences, and vegetation characteristics, machine learning (ML) models (Random Forest, XGBoost, LightGBM) were used to predict wildfire-prone areas using freely available active fire pixel data (MODIS Active Fire Collection 6 MCD14ML product). The evaluation of the trained ML models showed that the Random Forest (RF) model outperformed XGBoost and LightGBM, achieving the highest test accuracy (95.6%). All of the classifiers demonstrated a strong predictive performance, but RF excelled in sensitivity, specificity, precision, and F-1 score, making it the preferred model for generating a wildfire susceptibility map and conducting a SHAP analysis. Unlike prevailing approaches focusing solely on global feature importance, this study fills a critical gap by employing a SHAP summary and dependence plots to comprehensively assess each factor's contribution, enhancing the explainability and reliability of the results. The analysis reveals clear associations between factors such as wind speed, temperature, NDVI, slope, and distance to villages with increased fire susceptibility, while rainfall and distance to streams exhibit nuanced effects. The spatial distribution of the wildfire susceptibility classes highlights critical areas, particularly in flat and coastal regions near settlements and agricultural lands, emphasizing the need for enhanced awareness and preventive measures. These insights inform targeted fire management strategies, highlighting the importance of tailored interventions like firebreaks and vegetation management. However, challenges remain, including ensuring the selected factors' adequacy across diverse regions, addressing potential biases from resampling spatially varied data, and refining the model for broader applicability. [ABSTRACT FROM AUTHOR]

Site-specific weed management employs image data to generate maps through various methodologies that classify pixels corresponding to crop, soil, and weed. Further, many studies have focused on identifying specific weed species using spectral data. Nonetheless, the availability of open-access weed datasets remains limited. Remarkably, despite the extensive research employing hyperspectral imaging data to classify species under varying conditions, to the best of our knowledge, there are no open-access hyperspectral weed datasets. Consequently, accessible spectral weed datasets are primarily RGB or multispectral and mostly lack the temporal aspect, i.e., they contain a single measurement day. This paper introduces an open dataset for training and evaluating machine-learning methods and spectral features to classify weeds based on various biological traits. The dataset comprises 30 hyperspectral images, each containing thousands of pixels with 204 unique visible and near-infrared bands captured in a controlled environment. In addition, each scene includes a corresponding RGB image with a higher spatial resolution. We included three weed species in this dataset, representing different botanical groups and photosynthetic mechanisms. In addition, the dataset contains meticulously sampled labeled data for training and testing. The images represent a time series of the weed's growth along its early stages, critical for precise herbicide application. We conducted an experimental evaluation to test the performance of a machine-learning approach, a deep-learning approach, and Spectral Mixture Analysis (SMA) to identify the different weed traits. In addition, we analyzed the importance of features using the random forest algorithm and evaluated the performance of the selected algorithms while using different sets of features. [ABSTRACT FROM AUTHOR]

The goal of this study was to develop a model describing the relationship between the ground-displacement-caused tremors induced by underground mining, and mining and geological factors using the Random Forest Regression machine learning method. The Rudna mine (Poland) was selected as the research area, which is one of the largest deep copper ore mines in the world. The SAR Interferometry methods, Differential Interferometric Synthetic Aperture Radar (DInSAR) and Small Baseline Subset (SBAS), were used in the first case to detect line-of-sight (LOS) displacements, and in the second case to detect cumulative LOS displacements caused by mining tremors. The best-prediction LOS displacement model was characterized by R2 = 0.93 and RMSE = 5 mm, which proved the high effectiveness and a high degree of explanation of the variation of the dependent variable. The identified statistically significant driving variables included duration of exploitation, the area of the exploitation field, energy, goaf area, and the average depth of field exploitation. The results of the research indicate the great potential of the proposed solutions due to the availability of data (found in the resources of each mine), and the effectiveness of the methods used. [ABSTRACT FROM AUTHOR]

The eastern coastline of James Bay is known to have been home to sizeable eelgrass beds (Zostera marina L.) which thrived in the bay's shallow, subarctic waters. The region was subjected to substantial hydroelectric dams, large fires, and other human activities in the past half-century. To assess the impact of these factors on eelgrass beds, a historical reconstruction of eelgrass bed distribution was performed from images acquired by Landsat-5 Thematic Mapper (TM) in 1988, 1991, and 1996 and images of the Landsat-8 Operational Land Imager (OLI) in 2019. All the images were classified using the Random Forests classifier (RF) and assessed for accuracy each year on a bay-wide scale using an independent field validation dataset. The validation data were extracted from an eelgrass bed map established using aerial photos and field surveys in 1986, 1991, and 1995 and from a field survey in 2019. The overall validation accuracy of the classified images (between 72% and 85%) showed good agreement with the other datasets for most locations, providing reassurance about the reliability of the research. This makes it possible to use satellite imagery to detect past changes to eelgrass distribution within a bay. The classified images of 1988 and 1996 were also compared to aerial photos taken in years close to each other at ten sites to determine their ability to assess small eelgrass beds' shape and presence. Such a comparison revealed that the classified images accurately portrayed eelgrass distribution even at finer scales. [ABSTRACT FROM AUTHOR]

On a global scale, wetlands are suffering from a steady decline in surface area and environmental quality. Protecting them is essential and requires a careful spatialisation of their natural habitats. Traditionally, in our study area, species discrimination for floristic mapping has been achieved through on-site field inventories, but this approach is very time-consuming in these difficult-to-access environments. Usually, the resulting maps are also not spatially exhaustive and are not frequently updated. In this paper, we propose to establish a complete map of the study area using remote sensors and set up a long-term and regular observatory of environmental changes to monitor the evolution of a major French wetland. This methodology combines three dataset acquisition technologies, airborne hyperspectral and WorldView-3 multispectral images, supplemented by LiDAR images, which we compared to evaluate the difference in performances. To do so, we applied the Random Forest supervised classification methods using ground reference areas and compared the out-of-bag score (OOB score) as well as the matrix of confusion resulting from each dataset. Thirteen habitats were discriminated at level 4 of the European Nature Information System (EUNIS) typology, at a spatial resolution of around 1.2 m. We first show that a multispectral image with 19 variables produces results which are almost as good as those produced by a hyperspectral image with 58 variables. The experiment with different features also demonstrates that the use of four bands derived from LiDAR datasets can improve the quality of the classification. Invasive alien species Ludwigia grandiflora and Crassula helmsii were also detected without error which is very interesting when applied to these endangered environments. Therefore, since WV-3 images provide very good results and are easier to acquire than airborne hyperspectral data, we propose to use them going forward for the regular observation of the Brière marshes habitat we initiated. [ABSTRACT FROM AUTHOR]

Effective planning and management strategies for restoring and conserving tropical peat swamp ecosystems require accurate and timely estimates of aboveground biomass (AGB), especially when monitoring the impacts of restoration interventions. The aim of this research is to assess changes in AGB and evaluate the effectiveness of restoration efforts in the North Selangor Peat Swamp Forest (NSPSF), one of the largest remaining peat swamp forests in Peninsular Malaysia, using advanced remote sensing techniques. A Random Forest machine learning method was employed to upscale AGB estimates, derived from a 'LiDAR AGB model', to larger landscape-scale areas with Sentinel-2 spectral and textural variables. The time period under investigation (2015–2018) marked a concentrated phase of restoration and regeneration efforts in NSPSF. The results demonstrate an overall increase in tropical peat swamp AGB during these years, where the total amount of estimated AGB stored in NSPSF increased from 19.3 Tg in 2015 to an estimated 19.8 Tg in 2018. The research found that a tailored variable selection approach improved predictions of AGB, with optimised input variables (n = 62) and parameter adjustments producing a good plausible result (R2 = 0.80; RMSE = 55.2 Mg/ha). This paper concludes by emphasizing the importance of long-term studies (>5 years) for analyzing the success of tropical peat swamp restoration methods, with a potential for integrating remote sensing technology. [ABSTRACT FROM AUTHOR]

In organic farming, clover is an important basis for green manure in crop rotation systems due to its nitrogen-fixing effect. However, clover is often sown in mixtures with grass to achieve a yield-increasing effect. In order to determine the quantity and distribution of clover and its influence on the subsequent crops, clover plants must be identified at the individual plant level and spatially differentiated from grass plants. In practice, this is usually done by visual estimation or extensive field sampling. High-resolution unmanned aerial vehicles (UAVs) offer a more efficient alternative. In the present study, clover and grass plants were classified based on spectral information from high-resolution UAV multispectral images and texture features using a random forest classifier. Three different timestamps were observed in order to depict the phenological development of clover and grass distributions. To reduce data redundancy and processing time, relevant texture features were selected based on a wrapper analysis and combined with the original bands. Including these texture features, a significant improvement in classification accuracy of up to 8% was achieved compared to a classification based on the original bands only. Depending on the phenological stage observed, this resulted in overall accuracies between 86% and 91%. Subsequently, high-resolution UAV imagery data allow for precise management recommendations for precision agriculture with site-specific fertilization measures. [ABSTRACT FROM AUTHOR]

Salinization is a major soil degradation process threatening ecosystems and posing a great challenge to sustainable agriculture and food security worldwide. This study aimed to evaluate the potential of state-of-the-art machine learning algorithms in soil salinity (EC1:5) mapping. Further, we predicted the distribution patterns of soil salinity under different future scenarios in the Yellow River Delta. A geodatabase comprising 201 soil samples and 19 conditioning factors (containing data based on remote sensing images such as Landsat, SPOT/VEGETATION PROBA-V, SRTMDEMUTM, Sentinel-1, and Sentinel-2) was used to compare the predictive performance of empirical bayesian kriging regression, random forest, and CatBoost models. The CatBoost model exhibited the highest performance with both training and testing datasets, with an average MAE of 1.86, an average RMSE of 3.11, and an average R2 of 0.59 in the testing datasets. Among explanatory factors, soil Na was the most important for predicting EC1:5, followed by the normalized difference vegetation index and soil organic carbon. Soil EC1:5 predictions suggested that the Yellow River Delta region faces severe salinization, particularly in coastal zones. Among three scenarios with increases in soil organic carbon content (1, 2, and 3 g/kg), the 2 g/kg scenario resulted in the best improvement effect on saline–alkali soils with EC1:5 > 2 ds/m. Our results provide valuable insights for policymakers to improve saline–alkali land quality and plan regional agricultural development. [ABSTRACT FROM AUTHOR]

The population of Africa is expected to rise to 2.5 billion by 2050, with more than 80% of this increase concentrated in cities. Africa's anticipated population growth has serious implications for urban resource utilization and management, necessitating multi-level monitoring efforts that can inform planning and decision-making. Commonly, broad extent (e.g., country level) urban change analyses only examine a homogenous "developed" or "built-up" area, which may not capture patterns influenced by the heterogeneity of landscape features within urban areas. Contrarily, studies examining landscape heterogeneity at a finer resolution are typically limited in spatial extent (e.g., single city level). The goal of this study was to develop and test a hierarchical integrated mapping framework using globally available Earth Observation data (e.g., Landsat, Sentinel-2, Sentinel-1, and nightlight imagery) and accessible methodologies to produce national-level land use (LU) and urban-level land cover (LC) map products which may support a range of global and local monitoring and planning initiatives. We test our multi-tier methodology across three rapidly urbanizing African countries for the 2016–2020 period: Ethiopia, Nigeria, and South Africa. The initial output of our methodology includes annual national land use maps (Tier 1) for the purpose of delineating the dynamic boundaries of individual urban areas and monitoring national LU change. To complement Tier 1 LU maps, we detailed urban heterogeneity through LC classifications within urban areas (Tier 2) delineated using Tier 1 LU maps. Based on country-optimized sets of selected features that leverage spatial/texture and temporal dimensions of available data, we obtained an overall map accuracy of between 65 and 80% for Tier 1 maps and between 60 and 80% for Tier 2 maps, dependent on the evaluation country, although with consistent performance across study years providing a solid foundation for monitoring changes. We demonstrate the potential applications for our products through various analyses, including urbanization-driven LU change, and examine LC urban patterns across the three African study countries. While our findings allude to general differences in urban patterns across national scales, further analyses are needed to better understand the complex drivers behind urban LC configurations and their change patterns across different countries, city sizes, and rates of urbanization. Our multi-tier mapping framework is a viable strategy for producing harmonious, multi-level LULC products in developing countries using publicly available data and methodologies, which can serve as a basis for a wide range of informative and insightful monitoring analyses. [ABSTRACT FROM AUTHOR]

Marine ecosystems serve as vital indicators of biodiversity, providing habitats for diverse flora and fauna. Canada's extensive coastal regions encompass a rich range of marine habitats, necessitating accurate mapping techniques utilizing advanced technologies, such as remote sensing (RS). This study focused on a study area in Pistolet Bay in Newfoundland and Labrador (NL), Canada, with an area of approximately 170 km2 and depths varying between 0 and −28 m. Considering the relatively large coverage and shallow depths of water of the study area, it was decided to use airborne bathymetric Light Detection and Ranging (LiDAR) data, which used green laser pulses, to map the marine habitats in this region. Along with this LiDAR data, Remotely Operated Vehicle (ROV) footage, high-resolution multispectral drone imagery, true color Google Earth (GE) imagery, and shoreline survey data were also collected. These datasets were preprocessed and categorized into five classes of Eelgrass, Rockweed, Kelp, Other vegetation, and Non-Vegetation. A marine habitat map of the study area was generated using the features extracted from LiDAR data, such as intensity, depth, slope, and canopy height, using an object-based Random Forest (RF) algorithm. Despite multiple challenges, the resulting habitat map exhibited a commendable classification accuracy of 89%. This underscores the efficacy of the developed Artificial Intelligence (AI) model for future marine habitat mapping endeavors across the country. [ABSTRACT FROM AUTHOR]

Detailed information on forest tree species is crucial to inform management and policy and support environmental and ecological research. Sentinel-2 imagery is useful for obtaining spatially explicit and frequent information on forest tree species due to its suitable spatial, spectral, and temporal resolutions. However, classification workflows often do not generalise well to time periods that are not seen by the model during the calibration phase. This study investigates the temporal transferability of dominant tree species classification. To this end, the Random Forest, Support Vector Machine, and Multilayer Perceptron algorithms were used to classify five tree species in Flanders (Belgium) with regularly spaced Sentinel-2 time series from 2018 to 2022. Cross-year single-year input scenarios were compared with same-year single-year input scenarios to quantify the temporal transferability of the five evaluated years. This resulted in a decrease in overall accuracy between 2.30 and 14.92 percentage points depending on the algorithm and evaluated year. Moreover, our results indicate that the cross-year classification performance could be improved by using multi-year training data, reducing the drop in overall accuracy. In some cases, gains in overall accuracy were even observed. This study highlights the importance of including interannual spectral variability during the training stage of tree species classification models to improve their ability to generalise in time. [ABSTRACT FROM AUTHOR]

Rocky coastlines are characterised by steep cliffs, which frequently experience a variety of natural processes that often exhibit intricate interdependencies, such as rainfall, ice and water run-off, and marine actions. The advent of high temporal and spatial resolution data, that can be acquired through remote sensing and geomatics techniques, has facilitated the safe exploration of otherwise inaccessible areas. The datasets that can be gathered from these techniques, typically combined with data from fieldwork, can subsequently undergo analyses employing/applying machine learning algorithms and/or numerical modeling, in order to identify/discern the predominant influencing factors affecting cliff top erosion. This study focuses on a specific case situated at the Conero promontory of the Adriatic Sea in the Marche region. The research methodology entails several steps. Initially, the morphological, geological and geomechanical characteristics of the areas were determined through unmanned aerial vehicle (UAV) and conventional geological/geomechanical surveys. Subsequently, cliff top retreat was determined within a GIS environment by comparing orthophotos taken in 1978 and 2022 using the DSAS tool (Digital Shoreline Analysis System), highlighting cliff top retreat up to 50 m in some sectors. Further analysis was conducted via the use of two Machine Learning (ML) algorithms, namely Random Forest (RF) and eXtreme Gradient Boosting (XGB). The Mean Decrease in Impurity (MDI) methodology was employed to assess the significance of each factor. Both algorithms yielded congruent results, emphasising that cliff top erosion rates are primarily influenced by slope height. Finally, a validation of the ML algorithm results was conducted using 2D Limit Equilibrium Method (LEM) codes. Ten sections extracted from the sector experiencing the most substantial cliff top retreat, as identified by DSAS, were utilised for 2D LEM analysis. Factor of Safety (FS) values were identified and compared with the cliff height of each section. The results from the 2D LEM analyses corroborated the outputs of the ML algorithms, showing a strong correlation between the slope instability and slope height (R2 of 0.84), with FS decreasing with slope height. [ABSTRACT FROM AUTHOR]

In this study, we utilized a feature optimization method combining texture and topographical factors with the random forest (RF) approach to identify changes in the extent of the debris cover around the Tianshan Tomur Peak between 1989 and 2022. Based on Sentinel-1 image data, we extracted glacier flow velocities using an offset tracking method and conducted a long-term analysis of flow velocities in combination with existing datasets. The debris identification results for 2022 showed that the debris-covered area in the study region was 409.2 km2, constituting 22.8% of the total glacier area. Over 34 years, the area of debris cover expanded by 69.4 km2, reflecting a growth rate of 20.0%. Analysis revealed that glaciers in the Tomur Peak area have been decelerating at an overall rate of −4.0% per decade, with the complexity of the glacier bed environment and the instability of the glacier's internal structure contributing to significant seasonal and interannual variability in the movement speeds of individual glaciers. [ABSTRACT FROM AUTHOR]

Vegetation vertical complexity influences biodiversity and ecosystem productivity. Rapid warming in the boreal region is altering patterns of vertical complexity. LiDAR sensors offer novel structural metrics for quantifying these changes, but their spatiotemporal limitations and their need for ecological context complicate their application and interpretation. Satellite variables can estimate LiDAR metrics, but retrievals of vegetation structure using optical reflectance can lack interpretability and accuracy. We compare vertical complexity from the airborne LiDAR Land Vegetation and Ice Sensor (LVIS) in boreal Canada and Alaska to plant functional type, optical, and phenological variables. We show that spring onset and green season length from satellite phenology algorithms are more strongly correlated with vegetation vertical complexity (R = 0.43–0.63) than optical reflectance (R = 0.03–0.43). Median annual temperature explained patterns of vegetation vertical complexity (R = 0.45), but only when paired with plant functional type data. Random forest models effectively learned patterns of vegetation vertical complexity using plant functional type and phenological variables, but the validation performance depended on the validation methodology (R2 = 0.50–0.80). In correlating satellite phenology, plant functional type, and vegetation vertical complexity, we propose new methods of retrieving vertical complexity with satellite data. [ABSTRACT FROM AUTHOR]

Landsat data have been used to derive forest canopy structure, height, and volume using machine learning models, i.e., giving computers the ability to learn from data and make decisions and predictions without being explicitly programmed, with training data provided by ground measurement or airborne lidar. This study explored the potential use of Landsat reflectance and airborne lidar data as training data to estimate canopy heights in the Brazilian Amazon forest and examined the impacts of Landsat reflectance products at different process levels and sample spatial autocorrelation on random forest modeling. Specifically, this study assessed the accuracy of canopy height predictions from random forest regression models impacted by three different Landsat 8 reflectance product inputs (i.e., USGS level 1 top of atmosphere reflectance, USGS level 2 surface reflectance, and NASA nadir bidirectional reflectance distribution function (BRDF) adjusted reflectance (NBAR)), sample sizes, training/test split strategies, and geographic coordinates. In the establishment of random forest regression models, the dependent variable (i.e., the response variable) was the dominant canopy heights at a 90 m resolution derived from airborne lidar data, while the independent variables (i.e., the predictor variables) were the temporal metrics extracted from each Landsat reflectance product. The results indicated that the choice of Landsat reflectance products had an impact on model accuracy, with NBAR data yielding more trustful results than the other products despite having higher RMSE values. Training and test split strategy also affected the derived model accuracy metrics, with the random sample split (randomly distributed training and test samples) showing inflated accuracy compared to the spatial split (training and test samples spatially set apart). Such inflation was induced by the spatial autocorrelation that existed between training and test data in the random split. The inclusion of geographic coordinates as independent variables improved model accuracy in the random split strategy but not in the spatial split, where training and test samples had different geographic coordinate ranges. The study highlighted the importance of data processing levels and the training and test split methods in random forest modeling of canopy height. [ABSTRACT FROM AUTHOR]

In recent years, the semantic segmentation model has been widely applied in fields such as the extraction of crops due to its advantages such as strong discrimination ability, high accuracy, etc. Currently, there is no standard set of ground true label data for major crops in China, and the visual interpretation process is usually time-consuming and laborious. The sample size also makes it difficult to support the model to learn enough ground features, resulting in poor generalisation ability of the model, which in turn makes the model difficult to apply in fine extraction tasks of large-area crops. In this study, a method to establish a pseudo-label sample set based on the random forest algorithm to train a semantic segmentation model (U-Net) was proposed to perform winter wheat extraction. With the help of the GEE platform, Winter Wheat Canopy Index (WCI) indicators were employed in this method to initially extract winter wheat, and training samples (i.e., pseudo labels) were built for the semantic segmentation model through the iterative process of "generating random sample points—random forest model training—winter wheat extraction"; on this basis, the U-net model was trained with multi-time series remote sensing images; finally, the U-Net model was employed to obtain the spatial distribution map of winter wheat in Henan Province in 2022. The results illustrated that: (1) Pseudo-label data were constructed using the random forest model in typical regions, achieving an overall accuracy of 97.53% under validation with manual samples, proving that its accuracy meets the requirements for U-Net model training. (2) Utilizing the U-Net model, U-Net++ model, and random forest model constructed based on pseudo-label data for 2022, winter wheat mapping was conducted in Henan Province. The extraction accuracy of the three models is in the order of U-Net model > U-Net++ model > random forest model. (3) Using the U-Net model to predict the winter wheat planting areas in Henan Province in 2019, although the extraction accuracy decreased compared to 2022, it still exceeded that of the random forest model. Additionally, the U-Net++ model did not achieve higher classification accuracy. (4) Experimental results demonstrate that deep learning models constructed based on pseudo-labels exhibit higher classification accuracy. Compared to traditional machine learning models like random forest, they have higher spatiotemporal adaptability and robustness, further validating the scientific and practical feasibility of pseudo-labels and their generation strategies, which are expected to provide a feasible technical pathway for intelligent extraction of winter wheat spatial distribution information in the future. [ABSTRACT FROM AUTHOR]

The distribution of forest-dominant tree species is crucial for ecosystem assessment. Remote sensing monitoring requires annual ground sample data, but consistent field surveys are challenging. This study addresses this by combining sample migration learning and machine learning for multi-year tree species classification in the Three Gorges Reservoir area in China. Using the continuous change detection and classification (CCDC) algorithm, sample data from 2023 were successfully migrated to 2018–2022, achieving high migration accuracy ( R 2 = 0.8303, RMSE = 4.64). Based on migrated samples, random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB) algorithms classified forest tree species with overall accuracies above 70% and Kappa coefficients above 0.6. XGB. They outperformed other algorithms, with classification accuracy of over 80% and Kappa above 0.75 in almost all years. The final map indicates stable distribution from 2018 to 2023, with eucalyptus covering over 40% of the forest area, followed by horsetail pine, fir, cypress, and wetland pine. [ABSTRACT FROM AUTHOR]

Atmospheric methane is one of the major greenhouse gases with a drastic impact on climate change. This study developed a random forest model to obtain a daily 5 km resolution atmospheric methane concentration dataset with full spatial coverage (100%) from 2019 to 2021 in mainland China, thereby filling the gap in the methane product data from the Tropospheric Monitoring Instrument (TROPOMI). The coefficients of determination for a sample-based and spatial-based cross-validation are 0.97 and 0.93, respectively. The average deviation of the seamless methane product reconstructed by the random forest model is less than 1%, validated with the measured methane concentration data from the Total Carbon Column Observing Network sites. Methane concentrations in China show a distribution of high in the east and south and low in the west and north. The high-concentration areas include Central China, the Sichuan Basin, the Pearl River Delta, and the Yangtze River Delta. In terms of time scale, the methane concentration has evident seasonal variation, as it is low in spring (average 1852 ppb) and winter (average 1881 ppb) and high in summer (average 1885 ppb) and autumn (average 1886 ppb). This is mainly due to the significant increase in emissions from rice cultivation and wetlands during the summer and autumn. During the COVID-19 pandemic, the methane concentration decreases significantly and then starts to return to normal around 70 days after the Lunar New Year, indicating that the seamless methane product can potentially detect anomalous changes in methane concentration. [ABSTRACT FROM AUTHOR]

Aerosol research is important for the protection of the ecological environment, the improvement of air quality, and as a response to climate change. In this study, a random forest (RF) estimation model of aerosol optical depth (AOD) and extinction coefficient vertical profiles was, respectively, established using Orbiting Carbon Observatory-2 (OCO-2) oxygen-A band (O2 A-band) data from China and its surrounding areas in 2016, combined with geographical information (longitude, latitude, and elevation) and viewing angle data. To address the high number of OCO-2 O2 A-band channels, principal component analysis (PCA) was employed for dimensionality reduction. The model was then applied to estimate the aerosol extinction coefficients for the region in 2017, and its validity was verified by comparing the estimated values with the Cloud-Aerosol Lidar Infrared Pathfinder Satellite Observations (CALIPSO) Level 2 extinction coefficients. In the comprehensive analysis of overall performance, an AOD model was initially constructed using variables, achieving a correlation coefficient (R) of 0.676. Subsequently, predictions for aerosol extinction coefficients were generated, revealing a satisfactory agreement between the predicted and the actual values in the vertical direction, with an R of 0.535 and a root mean square error (RMSE) of 0.107 km−1. Of the four seasons of the year, the model performs best in autumn (R = 0.557), while its performance was relatively lower in summer (R = 0.442). Height had a significant effect on the model, with both R and RMSE decreasing as height increased. Furthermore, the accuracy of aerosol profile inversion shows a dependence on AOD, with a better accuracy when AOD is less than 0.3 and RMSE can be less than 0.06 km−1. [ABSTRACT FROM AUTHOR]

A'nyemaqen Snow Mountain (ASM) is the largest glacier area in the Yellow River source area and has been experiencing significant ablation in recent years. To investigate spatial–temporal elevation changes in ASM, a 21–year Digital Elevation Model (DEM) time series was obtained using the MicMac ASTER (MMASTER) algorithm and ASTER L1A V003 data. It covers the period from January 2002 to January 2023. The mean elevation of ASM decreased by −7.88 ± 3.37 m during this period, with highly spatial variation. The elevation decrease occurred mainly in the lower elevations and opposite in the higher elevations. The corresponding elevation decrease was −12.99 ± 11.29 and −4.45 ± 11.36 m at the southern Yehelong Glacier and the northern Weigeledangxiong Glacier, respectively. Moreover, there exists a temporal variation in ASM. The maximum elevation was observed in February for both ASM and the southern Yehelong Glacier but March for Weigeledangxiong Glacier, with about 1 month lagged. With the elevation time series and climate data from ERA5 datasets, we applied the random forest technique and found that the temperature is the main factor to elevation change in ASM. Furthermore, the response of elevation changes to temperature appeared with a lag and varied with the location. Based on the elevation time series, the ARIMA model was further used to forecast the elevation changes in the next 5 years. All regions will experience the elevation decrease, with a mean decline −1.74 ± 0.39 m and a corresponding rate −0.35 ± 0.08 m/a in ASM. This is similar to that of −0.38 ± 0.16 m/a between 2002 and 2003, showing its stability in the near future. [ABSTRACT FROM AUTHOR]

A timely and accurately predicted grain yield can ensure regional and global food security. The scientific community is gradually advancing the prediction of regional-scale maize yield. However, the combination of various datasets while predicting the regional-scale maize yield using simple and accurate methods is still relatively rare. Here, we have used multi-source datasets (climate dataset, satellite dataset, and soil dataset), lasso algorithm, and machine learning methods (random forest, support vector, extreme gradient boosting, BP neural network, long short-term memory network, and K-nearest neighbor regression) to predict China's county-level maize yield. The use of multi-sourced datasets advanced the predicting accuracy of maize yield significantly compared to the single-sourced dataset. We found that the machine learning methods were superior to the lasso algorithm, while random forest, extreme gradient boosting, and support vector machine represented the most preferable methods for maize yield prediction in China (R2 ≥ 0.75, RMSE = 824–875 kg/ha, MAE = 626–651 kg/ha). The climate dataset contributed more to the prediction of maize yield, while the satellite dataset contributed to tracking the maize growth process. However, the methods' accuracies and the dominant variables affecting maize growth varied with agricultural regions across different geographic locations. Our research serves as an important effort to examine the feasibility of multi-source datasets and machine learning techniques for regional-scale maize yield prediction. In addition, the methodology we have proposed here provides guidance for reliable yield prediction of different crops. [ABSTRACT FROM AUTHOR]

Exploring the relationship and driving forces between supply–demand of ecosystem services (ESs) and urbanization can help solve the environmental problems and promote regional sustainable development. This study analyzed the spatio-temporal distribution characteristics of supply–demand of ESs and comprehensive urbanization level (CUL) in Shaanxi Province from 2010 to 2019 and assessed the coupling relationship between ecosystem service supply–demand ratio (ESSDR) and CUL using the coupling coordination degree (CCD) model. Random forests and geographically weighted regression methods were utilized to characterize the contribution and spatial distribution of the drivers of CCD. The results showed that: (1) except for habitat quality, the ESSDR of the other three types of services as well as the comprehensive services showed a decreasing trend, CUL exhibited increasing trend; (2) Although CCD was generally increasing, a significant portion (78.51%) of regions still remained uncoordinated, with relatively better coordination shown around the Guanzhong urban agglomeration, which has a higher urbanization level; (3) The CCD in Shaanxi Province was primarily influenced by local financial income, the secondary industry, and temperature forces. In regions with high and increasing CCD, the tertiary industry was the decisive force. In other areas, there were significant spatial variations in the driving forces. These findings provide a coupled and coordinated perspective for urban ecological management, which can provide scientific reference and practical guidance for cities with different development modes. [ABSTRACT FROM AUTHOR]

Chromophoric dissolved organic matter (CDOM) is a mixture of various types of organic matter and a useful parameter for monitoring complex inland surface waters. Remote sensing has been widely utilized to detect CDOM in various studies; however, in many cases, the dataset is relatively imbalanced in a single region. To address these concerns, data were acquired from hyperspectral images, field reflection spectra, and field monitoring data, and the imbalance problem was solved using a synthetic minority oversampling technique (SMOTE). Using the on-site reflectance ratio of the hyperspectral images, the input variables Rrs (452/497), Rrs (497/580), Rrs (497/618), and Rrs (684/618), which had the highest correlation with the CDOM absorption coefficient aCDOM (355), were extracted. Random forest and light gradient boosting machine algorithms were applied to create a CDOM prediction algorithm via machine learning, and to apply SMOTE, low-concentration and high-concentration datasets of CDOM were distinguished by 5 m−1. The training and testing datasets were distinguished at a 75%:25% ratio at low and high concentrations, and SMOTE was applied to generate synthetic data based on the training dataset, which is a sub-dataset of the original dataset. Datasets using SMOTE resulted in an overall improvement in the algorithmic accuracy of the training and test step. The random forest model was selected as the optimal model for CDOM prediction. In the best-case scenario of the random forest model, the SMOTE algorithm showed superior performance, with testing R2, absolute error (MAE), and root mean square error (RMSE) values of 0.838, 0.566, and 0.777 m−1, respectively, compared to the original algorithm's test values of 0.722, 0.493, and 0.802 m−1. This study is anticipated to resolve imbalance problems using SMOTE when predicting remote sensing-based CDOM. It is expected to produce and implement a machine learning model with improved reliable performance. [ABSTRACT FROM AUTHOR]

Landslide susceptibility denotes the likelihood of a disaster event under specific conditions. The assessment of landslide susceptibility has transitioned from qualitative to quantitative methods. With the integration of information technology in geological hazard analysis, a range of quantitative models for assessing landslide susceptibility has emerged and is now widely used. To compare and evaluate the accuracy of these models, this study focuses on Xupu County in Hunan Province, applying several models, including the CF model, FR model, CF-LR coupled model, FR-LR coupled model, SVM model, and RF model, to assess regional landslide susceptibility. ROC curves are used to evaluate the reliability of the model's predictions. The evaluation results reveal that the CF model (AUC = 0.756), FR model (AUC = 0.764), CF-LR model (AUC = 0.776), FR-LR model (AUC = 0.781), SVM model (AUC = 0.814), and RF model (AUC = 0.912) all have AUC values within the range of 0.7–0.9, indicating that the overall accuracy of the models is good and can provide a reference for landslide susceptibility zoning in the study area. Among these, the Random Forest model demonstrates the best accuracy for landslide susceptibility zoning in the study area. By extracting the extremely high susceptibility zones from the landslide susceptibility zonings obtained by six models, a comparative analysis of model adaptability was conducted. The results indicate that the Random Forest model has the best adaptability under specific conditions in Xupu County. [ABSTRACT FROM AUTHOR]

Accurate identification of the spatio-temporal planting structure and analysis of its driving factors in an irrigation district are the important bases for scientific and reasonable utilization of irrigation water resources. In pursuit of this goal, the training sample migration method combined with the random forest algorithm were used to classify land use and planting structure over 2001–2022 in the lower Yellow River Basin. Moreover, an econometric regression model was applied to quantify the driving factors of the change in the crop-planted area. The results illustrated that the identification method has relatively high accuracy in identifying historical periods of land use and planting structures, with the average kappa coefficient equating to 0.953. From 2001 to 2022, the area of cultivated land was the largest, with the proportion of the total area increasing from 45.72% to 58.12%. The planted area of winter wheat–summer maize rotation increased from 74.84% to 88.11% of the cultivated land. While the planted area of cotton declined by 96.36%, about 50% of cotton planting was converted to the winter wheat–summer maize rotation planting. The government policies about grain purchase and storage were the dominant factors for the change in the crop-planted area. This resulted in an increase of 63.32 × 103 ha and 63.98 × 103 ha in the planted area of winter wheat and summer maize, respectively. The findings are of great significance to the allocation of water resources in irrigation districts of the lower Yellow River Basin. [ABSTRACT FROM AUTHOR]

Aerosol microphysical properties, including aerosol particle size distribution, complex refractive index and concentration properties, are key parameters evaluating the impact of aerosols on climate, meteorology, and human health. High Spectral Resolution Lidar (HSRL) is an efficient tool for probing the vertical optical properties of aerosol particles, including the aerosol backscatter coefficient (β) and extinction coefficient (α), at multiple wavelengths. To swiftly process vast data volumes, address the ill-posedness of retrieval problems, and suit simpler lidar systems, this study proposes an algorithm (modified algorithm) for retrieving microphysical property profiles from the HSRL optical data targeting fine-mode aerosols, building upon a previous algorithm (basic algorithm). The modified algorithm is based on a look-up table (LUT) approach, combined with the k-nearest neighbor (k-NN) and random forest (RF) algorithms, and it optimizes the decision tree generation strategy, incorporating a self-posed scheme. In numerical simulation tests for different lidar configurations, the modified algorithm reduced retrieval errors by 41%, 30%, and 32% compared to the basic algorithm for 3β + 2α, 3β + 1α, and 2β + 1α, respectively, with a remarkable improvement of stability. In two observation scenes of a field campaign, the median relative errors of the effective radius for 3β + 2α were 6% and −3%, and the median absolute errors of single-scattering albedo were 0.012 and 0.005. This method represents a further step toward the use of the LUT approach, with the potential to provide effective and efficient aerosol microphysical retrieval for simpler lidar systems, which could advance our understanding of aerosols' climatic, meteorological, and health impacts. [ABSTRACT FROM AUTHOR]

Pasture degradation poses significant economic, social, and environmental impacts in the Brazilian savanna ecosystem. Despite these impacts, effectively detecting varying intensities of agronomic and biological degradation through remote sensing remains challenging. This study explores the potential of the eight-band PlanetScope SuperDove satellite constellation to discriminate between five classes of pasture degradation: non-degraded pasture (NDP); pastures with low- (LID) and moderate-intensity degradation (MID); severe agronomic degradation (SAD); and severe biological degradation (SBD). Using a set of 259 cloud-free images acquired in 2022 across five sites located in central Brazil, the study aims to: (i) identify the most suitable period for discriminating between various degradation classes; (ii) evaluate the Random Forest (RF) classification performance of different SuperDove attributes; and (iii) compare metrics of accuracy derived from two predicted scenarios of pasture degradation: a more challenging one involving five classes (NDP, LID, MID, SAD, and SBD), and another considering only non-degraded and severely degraded pastures (NDP, SAD, and SBD). The study assessed individual and combined sets of SuperDove attributes, including band reflectance, vegetation indices, endmember fractions from spectral mixture analysis (SMA), and image texture variables from Gray-level Co-occurrence Matrix (GLCM). The results highlighted the effectiveness of the transition from the rainy to the dry season and the period towards the beginning of a new seasonal rainy cycle in October for discriminating pasture degradation. In comparison to the dry season, more favorable discrimination scenarios were observed during the rainy season. In the dry season, increased amounts of non-photosynthetic vegetation (NPV) complicate the differentiation between NDP and SBD, which is characterized by high soil exposure. Pastures exhibiting severe biological degradation showed greater sensitivity to water stress, manifesting earlier reflectance changes in the visible and near-infrared bands of SuperDove compared to other classes. Reflectance-based classification yielded higher overall accuracy (OA) than the approaches using endmember fractions, vegetation indices, or texture metrics. Classifications using combined attributes achieved an OA of 0.69 and 0.88 for the five-class and three-class scenarios, respectively. In the five-class scenario, the highest F1-scores were observed for NDP (0.61) and classes of agronomic (0.71) and biological (0.88) degradation, indicating the challenges in separating low and moderate stages of pasture degradation. An initial comparison of RF classification results for the five categories of degraded pastures, utilizing reflectance data from MultiSpectral Instrument (MSI)/Sentinel-2 (400–2500 nm) and SuperDove (400–900 nm), demonstrated an enhanced OA (0.79 versus 0.66) with Sentinel-2 data. This enhancement is likely to be attributed to the inclusion of shortwave infrared (SWIR) spectral bands in the data analysis. Our findings highlight the potential of satellite constellation data, acquired at high spatial resolution, for remote identification of pasture degradation. [ABSTRACT FROM AUTHOR]

The seasonal temperature trends and ice phenology in the Great Slave Lake (GSL) are significantly influenced by inflow from the Slave River. The river undergoes a sequence of mechanical break-ups all the way to the GSL, initiating the GSL break-up process. Additionally, upstream water management practices impact the discharge of the Slave River and, consequently, the ice break-up of the GSL. Therefore, monitoring the break-up process at the Slave River Delta (SRD), where the river meets the lake, is crucial for understanding the cascading effects of upstream activities on GSL ice break-up. This research aimed to use Random Forest (RF) models to monitor the ice break-up processes at the SRD using a combination of satellite images with relatively high spatial resolution, including Landsat-5, Landsat-8, Sentinel-2a, and Sentinel-2b. The RF models were trained using selected training pixels to classify ice, open water, and cloud. The onset of break-up was determined by data-driven thresholds on the ice fraction in images with less than 20% cloud coverage. Analysis of break-up timing from 1984 to 2023 revealed a significant earlier trend using the Mann–Kendall test with a p-value of 0.05. Furthermore, break-up data in recent years show a high degree of variability in the break-up rate using images in recent years with better temporal resolution. [ABSTRACT FROM AUTHOR]

Monitoring pavement conditions is critical to pavement management and maintenance. Traditionally, pavement distress is mainly identified via accelerometers, videos, and laser scanning. However, the geographical coverage and temporal frequency are constrained by the limited amount of equipment and labor, which sometimes may delay road maintenance. By contrast, crowdsourced data, in a manner of crowdsensing, can provide real-time and valuable roadway information for extensive coverage. This study exploited crowdsourced Waze pothole and weather reports for pavement condition evaluation. Two surrogate measures are proposed, namely, the Pothole Report Density (PRD) and the Weather Report Density (WRD). They are compared with the Pavement Quality Index (PQI), which is calculated using laser truck data from the Tennessee Department of Transportation (TDOT). A geographically weighted random forest (GWRF) model was developed to capture the complicated relationships between the proposed measures and PQI. The results show that the PRD is highly correlated with the PQI, and the correlation also varies across the routes. It is also found to be the second most important factor (i.e., followed by pavement age) affecting the PQI values. Although Waze weather reports contribute to PQI values, their impact is significantly smaller compared to that of pothole reports. This paper demonstrates that surrogate pavement condition measures aggregated by crowdsourced data could be integrated into the state decision-making process by establishing nuanced relationships between the surrogated performance measures and the state pavement condition indices. The endeavor of this study also has the potential to enhance the granularity of pavement condition evaluation. [ABSTRACT FROM AUTHOR]

Cloud-based remote sensing has spurred the use of techniques to improve mapping accuracy where individual images may have lower quality, especially in areas with complex terrain or high cloud cover. This study investigates the influence of image compositing and multisource data fusion on the multitemporal land cover mapping of the Pagsanjan-Lumban and Baroro Watersheds in the Philippines. Ten random forest models for each study site were used, all using a unique combination of more than 100 different input features. These features fall under three general categories. First, optical features were derived from reflectance bands and ten spectral indices, which were further subdivided into annual percentile and seasonal median composites; second, radar features were derived from ALOS PALSAR by computing textural indices and a simple band ratio; and third, topographic features were computed from the ALOS GDSM. Then, accuracy metrics and McNemar's test were used to assess and compare the significance of about 90 pairwise model outputs. Data fusion significantly improved the accuracy of multitemporal land cover mapping in most cases. However, image composition had varied impacts for both sites. This could imply local characteristics and feature inputs as potential determinants of the ideal composite method. Hence, the iterative screening or optimization of both input features and composites is recommended to improve multitemporal mapping accuracy. [ABSTRACT FROM AUTHOR]