Search

In shallow water, Sentinel-2 multispectral imagery has only four visible bands and limited quantization levels, which easily leads to the occurrence of the same spectral profile but different depth (SSPBDD) phenomenon, resulting in a one-to-many relationship between water depth and spectral profile. Investigating the impact of this relationship on water depth inversion models is the main objective of this paper. The Stumpf model and three machine learning models (Random Forest, Support Vector Machine, and Mixture Density Network) are employed, and the performance of these models is analysed based on the spatial distribution of the training dataset and the input information composition of these models. The results show that the root mean square errors (RMSEs) of the depth inversion of Random Forest and Support Vector Machine are significantly affected by the spatial distribution of the training dataset, while minimal effects are observed for the Stumpf model and the Mixture Density Network model. The SSPBDD phenomenon is widespread in Sentinel-2 images at all depths, particularly between 5 m and 15 m, with most of the depth maximum difference of the SSPBDD pixels ranging from 0 to 5 m. The SSPBDDs phenomenon can significantly reduce the inversion accuracy of any model. The number and the depth maximum difference of the SSPBDDs pixels are the main influencing factors. However, by increasing the visible spectral information and the spatial neighbourhood information in the input layer of machine learning models, the inversion accuracy and stability of the models can be improved to a certain extent. Among the models, the Mixture Density Network achieves the best inversion accuracy and stability. [ABSTRACT FROM AUTHOR]

Comprehensive vegetation surveys are crucial for species selection and layout during the restoration of degraded island ecosystems. However, due to the poor accessibility of uninhabited islands, traditional quadrat surveys are time-consuming and labor-intensive, and it is challenging to fully identify the specific species and their spatial distributions. With miniaturized sensors and strong accessibility, high spatial and temporal resolution, Unmanned Aerial Vehicles (UAVs) have been extensively implemented for vegetation surveys. By collecting UAVs multispectral images and conducting field quadrat surveys on Anyu Island, we employ four machine learning models, namely Gradient Boosting Decision Tree (GBDT), Support Vector Machine (SVM), Random Forest (RF) and Multiple Classifier Systems (MCS). We aim to identify the dominant species and analyze their spatial distributions according to spectral characteristics, vegetation index, topographic factors, texture features, and canopy heights. The results indicate that SVM model achieves the highest (88.55%) overall accuracy (OA) (kappa coefficient = 0.87), while MCS model does not significantly improve it as expected. Acacia confusa has the highest OA among 7 dominant species, reaching 97.67%. Besides the spectral characteristics, the inclusion of topographic factors and texture features in the SVM model can significantly improve the OA of dominant species. By contrast, the vegetation index, particularly the canopy height even reduces it. The dominant species exhibit significant zonal distributions with distance from the coastline on the Anyu Island (p < 0.001). Our study provides an effective and universal path to identify and map the dominant species and is helpful to manage and restore the degraded vegetation on uninhabited islands. [ABSTRACT FROM AUTHOR]

Invasive noxious weed species (INWS) are typical poisonous plants and forbs that are considered an increasing threat to the native alpine grassland ecosystems in the Qinghai–Tibetan Plateau (QTP). Accurate knowledge of the continuous cover of INWS across complex alpine grassland ecosystems over a large scale is required for their control and management. However, the cooccurrence of INWS and native grass species results in highly heterogeneous grass communities and generates mixed pixels detected by remote sensors, which causes uncertainty in classification. The continuous coverage of INWS at the pixel level has not yet been achieved. In this study, objective 1 was to test the capability of Senginel-2 imagery at estimating continuous INWS cover across complex alpine grasslands over a large scale and objective 2 was to assess the performance of the state-of-the-art convolutional neural network-based regression (CNNR) model in estimating continuous INWS cover. Therefore, a novel CNNR model and a random forest regression (RFR) model were evaluated for estimating INWS continuous cover using Sentinel-2 imagery. INWS continuous cover was estimated directly from Sentinel-2 imagery with an R2 ranging from 0.88 to 0.93 using the CNNR model. The RFR model combined with multiple features had a comparable accuracy, which was slightly lower than that of the CNNR model, with an R2 of approximately 0.85. Twelve green band-, red-edge band-, and near-infrared band-related features had important contributions to the RFR model. Our results demonstrate that the CNNR model performs well when estimating INWS continuous cover directly from Sentinel-2 imagery, and the RFR model combined with multiple features derived from the Sentinel-2 imager can also be used for INWS continuous cover mapping. Sentinel-2 imagery is suitable for mapping continuous INWS cover across complex alpine grasslands over a large scale. Our research provides information for the advanced mapping of the continuous cover of invasive species across complex grassland ecosystems or, more widely, terrestrial ecosystems over large spatial areas using remote sensors such as Sentinel-2. [ABSTRACT FROM AUTHOR]

Powdery mildew significantly impacts the yield of natural rubber by being one of the predominant diseases that affect rubber trees. Accurate, non-destructive recognition of powdery mildew in the early stage is essential for the cultivation management of rubber trees. The objective of this study is to establish a technique for the early detection of powdery mildew in rubber trees by combining spectral and physicochemical parameter features. At three field experiment sites and in the laboratory, a spectroradiometer and a hand-held optical leaf-clip meter were utilized, respectively, to measure the hyperspectral reflectance data (350–2500 nm) and physicochemical parameter data of both healthy and early-stage powdery-mildew-infected leaves. Initially, vegetation indices were extracted from hyperspectral reflectance data, and wavelet energy coefficients were obtained through continuous wavelet transform (CWT). Subsequently, significant vegetation indices (VIs) were selected using the ReliefF algorithm, and the optimal wavelengths (OWs) were chosen via competitive adaptive reweighted sampling. Principal component analysis was used for the dimensionality reduction of significant wavelet energy coefficients, resulting in wavelet features (WFs). To evaluate the detection capability of the aforementioned features, the three spectral features extracted above, along with their combinations with physicochemical parameter features (PFs) (VIs + PFs, OWs + PFs, WFs + PFs), were used to construct six classes of features. In turn, these features were input into support vector machine (SVM), random forest (RF), and logistic regression (LR), respectively, to build early detection models for powdery mildew in rubber trees. The results revealed that models based on WFs perform well, markedly outperforming those constructed using VIs and OWs as inputs. Moreover, models incorporating combined features surpass those relying on single features, with an overall accuracy (OA) improvement of over 1.9% and an increase in F1-Score of over 0.012. The model that combines WFs and PFs shows superior performance over all the other models, achieving OAs of 94.3%, 90.6%, and 93.4%, and F1-Scores of 0.952, 0.917, and 0.941 on SVM, RF, and LR, respectively. Compared to using WFs alone, the OAs improved by 1.9%, 2.8%, and 1.9%, and the F1-Scores increased by 0.017, 0.017, and 0.016, respectively. This study showcases the viability of early detection of powdery mildew in rubber trees. [ABSTRACT FROM AUTHOR]

Quaking aspen is an important deciduous tree species across interior western U.S. forests. Existing maps of aspen distribution are based on Landsat imagery and often miss small stands (<0.09 ha or 30 m2), which rapidly regrow when managed or following disturbance. In this study, we present methods for deriving a new regional map of aspen forests using one year of Sentinel-1 (S1) and Sentinel-2 (S2) imagery in Google Earth Engine. Using observed annual phenology of aspen across the Southern Rockies and leveraging the frequent temporal resolution of S1 and S2, ecologically relevant seasonal imagery composites were developed. We derived spectral indices and radar textural features targeting the canopy structure, moisture, and chlorophyll content. Using spatial block cross-validation and Random Forests, we assessed the accuracy of different scenarios and selected the best-performing set of features for classification. Comparisons were then made with existing landcover products across the study region. The resulting map improves on existing products in both accuracy (0.93 average F1-score) and detection of smaller forest patches. These methods enable accurate mapping at spatial and temporal scales relevant to forest management for one of the most widely distributed tree species in North America. [ABSTRACT FROM AUTHOR]

Obtaining accurate and real-time spatial distribution information regarding crops is critical for enabling effective smart agricultural management. In this study, innovative decision fusion strategies, including Enhanced Overall Accuracy Index (E-OAI) voting and the Overall Accuracy Index-based Majority Voting (OAI-MV), were introduced to optimize the use of diverse remote sensing data and various classifiers, thereby improving the accuracy of crop/vegetation identification. These strategies were utilized to integrate crop/vegetation classification outcomes from distinct feature sets (including Gaofen-6 reflectance, Sentinel-2 time series of vegetation indices, Sentinel-2 time series of biophysical variables, Sentinel-1 time series of backscatter coefficients, and their combinations) using distinct classifiers (Random Forests (RFs), Support Vector Machines (SVMs), Maximum Likelihood (ML), and U-Net), taking two grain-producing areas (Site #1 and Site #2) in Haixi Prefecture, Qinghai Province, China, as the research area. The results indicate that employing U-Net on feature-combined sets yielded the highest overall accuracy (OA) of 81.23% and 91.49% for Site #1 and Site #2, respectively, in the single classifier experiments. The E-OAI strategy, compared to the original OAI strategy, boosted the OA by 0.17% to 6.28%. Furthermore, the OAI-MV strategy achieved the highest OA of 86.02% and 95.67% for the respective study sites. This study highlights the distinct strengths of various remote sensing features and classifiers in discerning different crop and vegetation types. Additionally, the proposed OAI-MV and E-OAI strategies effectively harness the benefits of diverse classifiers and multisource remote sensing features, significantly enhancing the accuracy of crop/vegetation classification. [ABSTRACT FROM AUTHOR]

Reliable and up-to-date training reference samples are imperative for land cover (LC) classification. However, such training datasets are not always available in practice. The sample migration method has shown remarkable success in addressing this challenge in recent years. This work investigated the application of Sentinel-1 (S1) and Sentinel-2 (S2) data in training sample migration. In addition, the impact of various spectral bands and polarizations on the accuracy of the migrated training samples was also assessed. Subsequently, combined S1 and S2 images were classified using the Support Vector Machines (SVM) and Random Forest (RF) classifiers to produce annual LC maps from 2017 to 2021. The results showed a higher accuracy (98.25%) in training sample migrations using both images in comparison to using S1 (87.68%) and S2 (96.82%) data independently. Among the LC classes, the highest accuracy in migrated training samples was found for water, built-up, bare land, grassland, cropland, and wetland. Inquiries on the efficiency of different spectral bands and polarization used in training sample migration showed that bands 4 and 8 and VV polarization in the water class were more important, while for the wetland class, bands 5, 6, 7, 8, and 8A together with VV polarization showed superior performance. The results showed that the RF classifier provided better performance than the SVM (higher overall, producer, and user accuracy). Overall, our findings suggested that shared use of S1 and S2 data can be used as a suitable means for producing up-to-date and high-quality training samples. [ABSTRACT FROM AUTHOR]

Soil organic carbon (SOC) measurements are an indicator of soil health and an important parameter for the study of land-atmosphere carbon fluxes. Field sampling provides precise measurements at the sample location but entails high costs and cannot provide detailed maps unless the sampling density is very high. Remote sensing offers the possibility to quantify SOC over large areas in a cost-effective way. As a result, numerous studies have sought to quantify SOC using Earth observation data with a focus on inter-field or regional distributions. This study took a different angle and aimed to map the spatial distribution of SOC at the intra-field scale, since this distribution provides important insights into the biophysiochemical processes involved in the retention of SOC. Instead of solely using spectral measurements to quantify SOC, topographic and spectral features act as predictor variables. The necessary data on study fields in South-East England was acquired through a detailed SOC sampling campaign, including a LiDAR survey flight. Multi-spectral Sentinel-2 data of the study fields were acquired for the exact day of the sampling campaign, and for an interval of 18 months before and after this date. Random Forest (RF) and Support Vector Regression (SVR) models were trained and tested on the spectral and topographical data of the fields to predict the observed SOC values. Five different sets of model predictors were assessed, by using independently and in combination, single and multidate spectral data, and topographical features for the SOC sampling points. Both, RF and SVR models performed best when trained on multi-temporal Sentinel-2 data together with topographic features, achieving validation root-mean-square errors (RMSEs) of 0.29% and 0.23% SOC, respectively. These RMSEs are competitive when compared with those found in the literature for similar models. The topographic wetness index (TWI) exhibited the highest permutation importance for virtually all models. Given that farming practices within each field are the same, this result suggests an important role of soil moisture in SOC retention. Contrary to findings in dryer climates or in studies encompassing larger areas, TWI was negatively related to SOC levels in the study fields, suggesting a different role of soil wetness in the SOC storage in climates characterized by excess rainfall and poorly drained soils. [ABSTRACT FROM AUTHOR]

Crop mapping using satellite imagery is crucial for agriculture applications. However, a fundamental challenge that hinders crop mapping progress is the scarcity of samples. The latest foundation model, Segment Anything Model (SAM), provides an opportunity to address this issue, yet few studies have been conducted in this area. This study investigated the parcel segmentation performance of SAM on commonly used medium-resolution satellite imagery (i.e., Sentinel-2 and Landsat-8) and proposed a novel automated sample generation framework based on SAM. The framework comprises three steps. First, an image optimization automatically selects high-quality images as the inputs for SAM. Then, potential samples are generated based on the masks produced by SAM. Finally, the potential samples are subsequently subjected to a sample cleaning procedure to acquire the most reliable samples. Experiments were conducted in Henan Province, China, and southern Ontario, Canada, using six proven effective classifiers. The effectiveness of our method is demonstrated through the combination of field-survey-collected samples and differently proportioned generated samples. Our results indicated that directly using SAM for parcel segmentation remains challenging, unless the parcels are large, regular in shape, and have distinct color differences from surroundings. Additionally, the proposed approach significantly improved the performance of classifiers and alleviated the sample scarcity problem. Compared to classifiers trained only by field-survey-collected samples, our method resulted in an average improvement of 16% and 78.5% in Henan and Ontario, respectively. The random forest achieved relatively good performance, with weighted-average F1 of 0.97 and 0.996 obtained using Sentinel-2 imagery in the two study areas, respectively. Our study contributes insights into solutions for sample scarcity in crop mapping and highlights the promising application of foundation models like SAM. [ABSTRACT FROM AUTHOR]

This study addresses a crucial gap in understanding the impact of urban morphologies on the canopy urban heat islands (CUHI) effect. The selection of reference stations lacks a unified standard, and their surface air temperature (SAT) sequences are also inevitably influenced by urbanization. However, synchronous observational data from relocated meteorological stations could provide high-quality sample data for studying CUHI. Utilizing remote sensing techniques, the findings of this paper revealed that the observation environment of stations after relocation exhibited remarkable representativeness, with their observation sequences accurately reflecting the local climatic background. The differences in synchronized observation sequences could characterize the CUHI intensity (CUHII). Among the various factors, land use parameters and landscape parameters played particularly significant roles. Furthermore, the fitting performance of the random forest (RF) model for both training and testing data was significantly superior to that of the linear model and support vector regression (SVR) model. Additionally, the influence of local circulation on CUHI could not be overlooked. The mechanisms by which urban morphologies affect CUHII under different circulation backgrounds deserve further investigation. [ABSTRACT FROM AUTHOR]

Red needle cast (RNC), mainly caused by Phytophthora pluvialis, is a very damaging disease of the widely grown species radiata pine within New Zealand. Using a combination of satellite imagery and weather data, a novel methodology was developed to pre-visually predict the incidence of RNC on radiata pine within the Gisborne region of New Zealand over a five-year period from 2019 to 2023. Sentinel-2 satellite imagery was used to classify areas within the region as being disease-free or showing RNC expression from the difference in the red/green index (R/Gdiff) during a disease-free time of the year and the time of maximum disease expression in the upper canopy (early spring–September). Within these two classes, 1976 plots were extracted, and a classification model was used to predict disease incidence from mean monthly weather data for key variables during the 11 months prior to disease expression. The variables in the final random forest model included solar radiation, relative humidity, rainfall, and the maximum air temperature recorded during mid–late summer, which provided a pre-visual prediction of the disease 7–8 months before its peak expression. Using a hold-out test dataset, the final random forest model had an accuracy of 89% and an F1 score of 0.89. This approach can be used to mitigate the impact of RNC by focusing on early surveillance and treatment measures. [ABSTRACT FROM AUTHOR]

Accurate mapping of forest habitats, especially in NATURA sites, is essential information for forest monitoring and sustainable management but also for habitat characterisation and ecosystem functioning. Remote sensing data and spatial modelling allow accurate mapping of the presence and distribution of tree species and habitats and are valuable tools for the long-term assessment of habitat status required by the European Commission. In order to serve the above, the present study aims to propose a methodology to accurately map the spatial distribution of forest habitats in three NATURA2000 sites of Cyprus by employing Sentinel-1 and Sentinel-2 data as well as topographic features using the Google Earth Engine (GEE). A pivotal aspect of the methodology identified was that the best band combination of the Random Forest (RF) classifier achieves the highest performance for mapping the dominant habitats in the three case studies. Specifically, in the Akamas region, eight habitat types have been mapped, in Paphos nine and six in Troodos. These habitat types are included in three of the nine habitat groups based on the EU's Habitat Directive: the sclerophyllous scrub, rocky habitats and caves and forests. The results show that using the RF algorithm achieves the highest performance, especially using Dataset 6, which is based on S2 bands, spectral indices and topographical features, and Dataset 13, which includes S2, S1, spectral indices and topographical features. These datasets achieve an overall accuracy (OA) of approximately 91–94%. In contrast, Dataset 7, which includes only S1 bands and Dataset 9, which combines S1 bands and spectral indices, achieve the lowest performance with an OA of approximately 25–43%. [ABSTRACT FROM AUTHOR]

Southern China, one of the traditional rice production bases, has experienced significant declines in the area of rice paddy since the beginning of this century. Monitoring the rice cropping area is becoming an urgent need for food security policy decisions. One of the main challenges for mapping rice in this area is the quantity of cloud-free observations that are vulnerable to frequent cloud cover. Another relevant issue that needs to be addressed is determining how to select the appropriate classifier for mapping paddy rice based on the cloud-masked observations. Therefore, this study was organized to quickly find a strategy for rice mapping by evaluating cloud-mask algorithms and machine-learning methods for Sentinel-2 imagery. Specifically, we compared four GEE-embedded cloud-mask algorithms (QA60, S2cloudless, CloudScore, and CDI (Cloud Displacement Index)) and analyzed the appropriateness of widely accepted machine-learning classifiers (random forest, support vector machine, classification and regression tree, gradient tree boost) for cloud-masked imagery. The S2cloudless algorithm had a clear edge over the other three algorithms based on its overall accuracy in evaluation and visual inspection. The findings showed that the algorithm with a combination of S2cloudless and random forest showed the best performance when comparing mapping results with field survey data, referenced rice maps, and statistical yearbooks. In general, the research highlighted the potential of using Sentinel-2 imagery to map paddy rice with multiple combinations of cloud-mask algorithms and machine-learning methods in a cloud-prone area, which has the potential to broaden our rice mapping strategies. [ABSTRACT FROM AUTHOR]

Precipitation is the basic component of the Earth's water cycle. Obtaining high-resolution and high-precision precipitation data is of great significance. This paper establishes a precipitation retrieval model based on a random forest classification and regression model during the day and at night with FY-4B/AGRI Level1 data on China from July to August 2022. To evaluate the retrieval effect of the model, the GPM IMERG product is used as a reference, and the retrieval results are compared against those of the FY-4B/AGRI operational precipitation product. In addition, the retrieval results are analyzed according to different underlying surfaces. The results showed that compared with the FY-4B/AGRI operational precipitation product, the retrieval model can better identify precipitation and capture precipitation areas of light rain, moderate rain, heavy rain and torrential rain. Among them, the probability of detection (POD) of the day model increased from 0.328 to 0.680, and the equitable threat score (ETS) increased from 0.252 to 0.432. The POD of the night model increased from 0.337 to 0.639, and the ETS score increased from 0.239 to 0.369. Meanwhile, the precipitation estimation accuracy of the day model increased by 38.98% and that of the night model increased by 40.85%. Our results also showed that due to the surface uniformity of the ocean, the model can identify precipitation better on the ocean than on the land. Our findings also indicated that for the different underlying surfaces of the land, there is no significant difference in each evaluation index of the model. This is a strong argument for the universal applicability of the model. Notably, the results showed that, especially for more vegetated areas and areas covered by water, the model is capable of estimating precipitation. In conclusion, the precipitation retrieval model that is proposed herein can better determine precipitation regions and estimate precipitation intensities compared with the FY-4B/AGRI operational precipitation product. It can provide some reference value for future precipitation retrieval research on FY-4B/AGRI. [ABSTRACT FROM AUTHOR]

Mapping benthic habitats with bathymetric, acoustic, and spectral data requires georeferenced ground-truth information about habitat types and characteristics. New technologies like autonomous underwater vehicles (AUVs) collect tens of thousands of images per mission making image-based ground truthing particularly attractive. Two types of machine learning (ML) models, random forest (RF) and deep neural network (DNN), were tested to determine whether ML models could serve as an accurate substitute for manual classification of AUV images for substrate type interpretation. RF models were trained to predict substrate class as a function of texture, edge, and intensity metrics (i.e., features) calculated for each image. Models were tested using a manually classified image dataset with 9-, 6-, and 2-class schemes based on the Coastal and Marine Ecological Classification Standard (CMECS). Results suggest that both RF and DNN models achieve comparable accuracies, with the 9-class models being least accurate (~73–78%) and the 2-class models being the most accurate (~95–96%). However, the DNN models were more efficient to train and apply because they did not require feature estimation before training or classification. Integrating ML models into benthic habitat mapping process can improve our ability to efficiently and accurately ground-truth large areas of benthic habitat using AUV or similar images. [ABSTRACT FROM AUTHOR]

The production of "Nocciola Romana" hazelnuts in the province of Viterbo, Italy, has evolved into a highly efficient and profitable agro-industrial system. Our approach is based on a hierarchical framework utilizing aggregated data from multiple temporal data and sources, offering valuable insights into the spatial, temporal, and phenological distributions of hazelnut crops To achieve our goal, we harnessed the power of Google Earth Engine and utilized collections of satellite images from Sentinel-2 and Sentinel-1. By creating a dense stack of multi-temporal images, we precisely mapped hazelnut groves in the area. During the testing phase of our model pipeline, we achieved an F1-score of 99% by employing a Hierarchical Random Forest algorithm and conducting intensive sampling using high-resolution satellite imagery. Additionally, we employed a clustering process to further characterize the identified areas. Through this clustering process, we unveiled distinct regions exhibiting diverse spatial, spectral, and temporal responses. We successfully delineated the actual extent of hazelnut cultivation, totaling 22,780 hectares, in close accordance with national statistics, which reported 23,900 hectares in total and 21,700 hectares in production for the year 2022. In particular, we identified three distinct geographic distribution patterns of hazelnut orchards in the province of Viterbo, confined within the PDO (Protected Designation of Origin)-designated region. The methodology pursued, using three years of aggregate data and one for SAR with a spectral separation clustering hierarchical approach, has effectively allowed the identification of the specific perennial crop, enabling a deeper characterization of various aspects influenced by diverse environmental configurations and agronomic practices.The accurate mapping and characterization of hazelnut crops open opportunities for implementing precision agriculture strategies, thereby promoting sustainability and maximizing yields in this thriving agro-industrial system. [ABSTRACT FROM AUTHOR]

The TROPOMI XCH4 data product requires rigorous cloud filtering to achieve a product accuracy of <1%. To this end, operational XCH4 data processing has been based on SUOMI-NPP VIIRS cloud observations. However, SUOMI-NPP is nearing the end of its operational life and has encountered malfunctions in 2022 and 2023. In this study, we introduce a novel machine learning cloud-clearing approach based on a random forest classifier (RFC). The RFC is trained on collocated TROPOMI and SUOMI-NPP VIIRS data to emulate VIIRS-like cloud clearing. After training, cloud masking requires only TROPOMI data, and so becomes operationally independent of SUOMI-NPP. We demonstrate the RFC approach by applying cloud clearing to operational TROPOMI XCH4 data for August 2022, a period in which VIIRS was not operational. For validation, we analyze the TROPOMI XCH4 data at 12 TCCON stations. Comparison of cloud clearing using the RFC and the original VIIRS method reveals excellent agreement with a similar station-to-station bias (−7.4 ppb versus −5.6 ppb), a similar standard deviation of the station-to-station bias (11.6 ppb versus 12 ppb), and the same Pearson correlation coefficient of 0.9. Remarkably, the RFC cloud clearing provides a slightly higher volume of data (2182 versus 2035 daily means) and appears to have fewer outliers. Since 21 November 2023, the RFC approach is part of the operational processing chain of the European Space Agency (ESA). For now, the default practice is to utilize SNPP-VIIRS when accessible. Only in cases where VIIRS data are unavailable do we resort to the RFC cloud mask. [ABSTRACT FROM AUTHOR]

The increasing availability of products generating burned area (BA) maps in recent years necessitates the creation of more accurate reference perimeters to validate these products and provide users with information about their accuracy. For this purpose, reference perimeters were created using Sentinel-2 images in Latin America and the Caribbean (LAC) for the year 2019. The sampling was adapted to the peculiarities of the Sentinel-2 tiling grid system, and statistically representative sample units were selected for biomes and fire activity through stratified random sampling. Fire perimeters were extracted using a Random Forest supervised classification and results were manually supervised and refined. Efforts were made to maximize the temporal length covered by the reference perimeters for each sample, aiming to minimize temporal errors when using the perimeters for validation. The dataset covers 569,214.2 k m 2 (3.5% burned, 88.7% unburned, and 7.8% unobserved). These perimeters were compared with higher spatial resolution PlanetScope-derived perimeters, resulting in 8.4% commission errors and 3.8% omission errors. As a validation exercise, MCD64A1 and FireCCI51 global burned area products were validated using the Sentinel-2 reference dataset created, confirming that the temporal extent of the reference perimeters significantly affects the validation of such products. The reference fire perimeters are publicly available in the Burned Area Reference Database (BARD). [ABSTRACT FROM AUTHOR]

The aim of this study is to predict and map winter wheat yield in the Parvomay municipality, situated in the Upper Thracian Lowland of Bulgaria, utilizing satellite data from Sentinel-2. The main crops grown in the research area are winter wheat, rapeseed, sunflower, and maize. To distinguish winter wheat fields accurately, we evaluated classification methods such as Support Vector Machines (SVM) and Random Forest (RF). These methods were applied to satellite multispectral data acquired by the Sentinel-2 satellites during the growing season of 2020–2021. In accordance with their development cycles, temporal image composites were developed to identify suitable moments when each crop is most accurately distinguished from others. Ground truth data obtained from the integrated administration and control system (IACS) were used for training the classifiers and assessing the accuracy of the final maps. Winter wheat fields were masked using the crop mask created from the best-performing classification algorithm. Yields were predicted with regression models calibrated with in situ data collected in the Parvomay study area. Both SVM and RF algorithms performed well in classifying winter wheat fields, with SVM slightly outperforming RF. The produced crop maps enable the application of crop-specific yield models on a regional scale. The best predictor of yield was the green NDVI index (GNDVI) from the April monthly composite image. [ABSTRACT FROM AUTHOR]

The complexity of surface characteristics in rural areas poses challenges for accurate extraction of built-up areas from remote sensing images. The Artificial Surface Index (ASI) emerged as a novel and accurate built-up land index. However, the absence of short-wave infrared (SWIR) bands in most high-resolution (HR) images restricts the application of index-based methods in rural built-up land extraction. This paper presents a rapid extraction method for high-resolution built-up land in rural areas based on ASI. Through the downscaling techniques of random forest (RF) regression, high-resolution SWIR bands were generated. They were then combined with visible and near-infrared (VNIR) bands to compute ASI on GaoFen-2 (GF-2) images (called A S I G F ). Furthermore, a red roof index (RRI) was designed to reduce the probability of misclassifying built-up land with bare soil. The results demonstrated that SWIR downscaling effectively compensates for multispectral information absence in HR imagery and expands the applicability of index-based methods to HR remote sensing data. Compared with five other indices (UI, BFLEI, NDBI, BCI, and PISI), the combination of ASI and RRI achieved the optimal performance in built-up land enhancement and bare land suppression, particularly showcasing superior performance in rural built-up land extraction. [ABSTRACT FROM AUTHOR]

The identification of wetland vegetation is essential for environmental protection and management as well as for monitoring wetlands' health and assessing ecosystem services. However, some limitations on vegetation classification may be related to remote sensing technology, confusion between plant species, and challenges related to inadequate data accuracy. In this paper, vegetation classification in the Yancheng Coastal Wetlands is studied and evaluated from Sentinel-2 images based on a random forest algorithm. Based on consistent time series from remote sensing observations, the characteristic patterns of the Yancheng Coastal Wetlands were better captured. Firstly, the spectral features, vegetation indices, and phenological characteristics were extracted from remote sensing images, and classification products were obtained by constructing a dense time series using a dataset based on Sentinel-2 images in Google Earth Engine (GEE). Then, remote sensing classification products based on the random forest machine learning algorithm were obtained, with an overall accuracy of 95.64% and kappa coefficient of 0.94. Four indicators (POP, SOS, NDVIre, and B12) were the main contributors to the importance of the weight analysis for all features. Comparative experiments were conducted with different classification features. The results show that the method proposed in this paper has better classification. [ABSTRACT FROM AUTHOR]

Highly accurate data on urban and rural settlement (URS) are essential for urban planning and decision-making in response to climate and environmental changes. This study developed an optimal random forest classification model for URSs based on spectral–topographic–radar polarization features using Landsat 8, NASA DEM, and Sentinel-1 SAR as the remote-sensing data sources. An optimal urban and rural settlement boundary (URSB) extraction technique based on morphological and pixel-level statistical methods was established to link discontinuous URSs and improve the accuracy of URSB extraction. An optimal random forest classification model for URSs was developed, as well as a technique to optimize URSB, using the Google Earth Engine (GEE) platform. The URSB of Xining, China, in 2020 was then extracted at a spatial resolution of 30 m, achieving an overall accuracy and Kappa coefficient of 96.21% and 0.92, respectively. Compared to using a single spectral feature, these corresponding metrics improved by 16.21% and 0.35, respectively. This research also demonstrated that the newly constructed Blue Roof Index (BRI), with enhanced blue roof features, is highly indicative of URSs and that the URSB was best extracted when the window size of the structural elements was 13 × 13. These results can be used to provide technical support for obtaining highly accurate information on URSs. [ABSTRACT FROM AUTHOR]

Snow plays a crucial role in the global water cycle, providing water to over 20% of the world's population and serving as a vital component for flora, fauna, and climate regulation. Changes in snow patterns due to global warming have far-reaching impacts on water management, agriculture, and other economic sectors such as winter tourism. Additionally, they have implications for environmental stability, prompting migration and cultural shifts in snow-dependent communities. Accurate information on snow and its variables is, thus, essential for both scientific understanding and societal planning. This review explores the potential of remote sensing in monitoring snow water equivalent (SWE) on a large scale, analyzing 164 selected publications from 2000 to 2023. Categorized by methodology and content, the analysis reveals a growing interest in the topic, with a concentration of research in North America and China. Methodologically, there is a shift from passive microwave (PMW) inversion algorithms to artificial intelligence (AI), particularly the Random Forest (RF) and neural network (NN) approaches. A majority of studies integrate PMW data with auxiliary information, focusing thematically on remote sensing and snow research, with limited incorporation into broader environmental contexts. Long-term studies (>30 years) suggest a general decrease in SWE in the Northern Hemisphere, though regional and seasonal variations exist. Finally, the review suggests potential future SWE research directions such as addressing PMW data issues, downsampling for detailed analyses, conducting interdisciplinary studies, and incorporating forecasting to enable more widespread applications. [ABSTRACT FROM AUTHOR]

Monitoring salt marshes with remote sensing is necessary to evaluate their state and restoration. Determining appropriate techniques for this can be overwhelming. Our study provides insight into whether a pixel- or object-based Random Forest classification approach is best for mapping vegetation in north temperate salt marshes. We used input variables from drone images (raw reflectances, vegetation indices, and textural features) acquired in June, July, and August 2021 of a salt marsh restoration and reference site in Aulac, New Brunswick, Canada. We also investigated the importance of input variables and whether using landcover classes representing areas of change was a practical way to evaluate variation in the monthly images. Our results indicated that (1) the classifiers achieved overall validation accuracies of 91.1–95.2%; (2) pixel-based classifiers outperformed object-based classifiers by 1.3–2.0%; (3) input variables extracted from the August images were more important than those extracted from the June and July images; (4) certain raw reflectances, vegetation indices, and textural features were among the most important variables; and (5) classes that changed temporally were mapped with user's and producer's validation accuracies of 86.7–100.0%. Knowledge gained during this study will inform assessments of salt marsh restoration trajectories spanning multiple years. [ABSTRACT FROM AUTHOR]

Terrestrial LiDAR scanning (TLS) has the potential to revolutionize forestry by enabling the precise estimation of aboveground biomass, vital for forest carbon management. This study addresses the lack of comprehensive benchmarking for leaf-filtering algorithms used in TLS data processing and evaluates four widely recognized geometry-based leaf-filtering algorithms (LeWoS, TLSeparation, CANUPO, and a novel random forest model) across openly accessible TLS datasets from diverse global locations. Multiple evaluation dimensions are considered, including pointwise classification accuracy, volume comparisons using a quantitative structure model applied to wood points, computational efficiency, and visual validation. The random forest model outperformed the other algorithms in pointwise classification accuracy (overall accuracy = 0.95 ± 0.04), volume comparison (R-squared = 0.96, slope value of 0.98 compared to destructive volume), and resilience to reduced point cloud density. In contrast, TLSeparation exhibits the lowest pointwise classification accuracy (overall accuracy = 0.81 ± 0.10), while LeWoS struggles with volume comparisons (mean absolute percentage deviation ranging from 32.14 ± 29.45% to 49.14 ± 25.06%) and point cloud density variations. All algorithms show decreased performance as data density decreases. LeWoS is the fastest in terms of processing time. This study provides valuable insights for researchers to choose appropriate leaf-filtering algorithms based on their research objectives and forest conditions. It also hints at future possibilities for improved algorithm design, potentially combining radiometry and geometry to enhance forest parameter estimation accuracy. [ABSTRACT FROM AUTHOR]

At present, for business lightning positioning systems, the classification of lightning discharge types is mostly based on lightning pulse signal features, and there is still a lot of room for improvement. We propose a lightning discharge classification method based on convolutional encoding features. This method utilizes convolutional neural networks to extract encoding features, and uses random forests to classify the extracted encoding features, achieving high accuracy discrimination for various lightning discharge events. Compared with traditional multi-parameter-based methods, the new method proposed in this paper has the ability to identify multiple lightning discharge events and does not require precise detailed feature engineering to extract individual pulse parameters. The accuracy of this method for identifying lightning discharge types in intra-cloud flash (IC), cloud-to-ground flash (CG), and narrow bipolar events (NBEs) is 97%, which is higher than that of multi-parameter methods. Moreover, our method can complete the classification task of lightning signals at a faster speed. Under the same conditions, the new method only requires 28.2 µs to identify one pulse, while deep learning-based methods require 300 µs. This method has faster recognition speed and higher accuracy in identifying multiple discharge types, which can better meet the needs of real-time business positioning. [ABSTRACT FROM AUTHOR]

Drought is a frequent global phenomenon. Solar-induced chlorophyll fluorescence (SIF), an electromagnetic signal, has been proven to be an efficient tool for monitoring and assessing gross primary productivity (GPP) and drought. To address the issue of the sparse resolution of satellite-based SIF, researchers have developed different downscaling algorithms. Recently, the most frequently used SIF products had a spatial resolution of 0.05 degrees. However, these spatial resolution SIF data are not conducive to regional agricultural drought monitoring. In this study, we utilized the global 'OCO-2' solar-induced fluorescence (GOSIF) products along with normalized difference vegetation index (NDVI) and land surface temperature (LST) products. With the powerful advantages offered by Google Earth Engine (GEE), we could conveniently acquire the necessary data. Additionally, employing the random forest (RF) method, we successfully acquired downscaled SIF data at an enhanced spatial resolution of 1 km. Using those downscaled SIF results with 1 km resolution, an SIF anomaly index was established and calculated to monitor drought. Results showed that the RF-based downscaled SIF result followed the same trend as the GOSIF value. Subsequently, correlation coefficients between SIF and GPP were calculated. The downscaled SIF demonstrated a higher correlation with GPP from MODIS compared to 0.05-degree GOSIF, with coefficients of 0.74 and 0.68 in May 2018, respectively. Moreover, the SIF anomaly index showed positive correlations with crop yield; the correlation coefficients were 0.93 for wheat and 0.89 for maize. The drought index had a negative correlation with areas affected by drought, with a correlation coefficient of −0.58. Finally, the SIF anomaly index was used to monitor drought from 2001 to 2020 in Henan Province. The 1 km SIF results obtained through the RF-based downscaled method were deemed reliable, thereby establishing the suitability of the SIF anomaly index for drought monitoring at a regional scale. [ABSTRACT FROM AUTHOR]

Wetlands provide vital ecological and socioeconomic services but face escalating pressures worldwide. This study undertakes an integrated spatiotemporal assessment of the multifaceted vulnerabilities shaping Khinjhir Lake, an ecologically significant wetland ecosystem in Pakistan, using advanced geospatial and machine learning techniques. Multi-temporal optical remote sensing data from 2000 to 2020 was analyzed through spectral water indices, land cover classification, change detection and risk mapping to examine moisture variability, land cover modifications, area changes and proximity-based threats over two decades. The random forest algorithm attained the highest accuracy (89.5%) for land cover classification based on rigorous k-fold cross-validation, with a training accuracy of 91.2% and a testing accuracy of 87.3%. This demonstrates the model's effectiveness and robustness for wetland vulnerability modeling in the study area, showing 11% shrinkage in open water bodies since 2000. Inventory risk zoning revealed 30% of present-day wetland areas under moderate to high vulnerability. The cellular automata–Markov (CA–Markov) model predicted continued long-term declines driven by swelling anthropogenic pressures like the 29 million population growth surrounding Khinjhir Lake. The research demonstrates the effectiveness of integrating satellite data analytics, machine learning algorithms and spatial modeling to generate actionable insights into wetland vulnerability to guide conservation planning. The findings provide a robust baseline to inform policies aimed at ensuring the health and sustainable management and conservation of Khinjhir Lake wetlands in the face of escalating human and climatic pressures that threaten the ecological health and functioning of these vital ecosystems. [ABSTRACT FROM AUTHOR]

Automated built-up infrastructure classification is a global need for planning. However, individual indices have weaknesses, including spectral confusion with bare ground, and computational requirements for deep learning are intensive. We present a computationally lightweight method to classify built-up infrastructure. We use an ensemble of spectral indices and a novel red-band texture layer with global thresholds determined from 12 diverse sites (two seasonally varied images per site). Multiple spectral indexes were evaluated using Sentinel-2 imagery. Our texture metric uses the red band to separate built-up infrastructure from spectrally similar bare ground. Our evaluation produced global thresholds by evaluating ground truth points against a range of site-specific optimal index thresholds across the 24 images. These were used to classify an ensemble, and then spectral indexes, texture, and stratified random sampling guided training data selection. The training data fit a random forest classifier to create final binary maps. Validation found an average overall accuracy of 79.95% (±4%) and an F1 score of 0.5304 (±0.07). The inclusion of the texture metric improved overall accuracy by 14–21%. A comparison to site-specific thresholds and a deep learning-derived layer is provided. This automated built-up infrastructure mapping framework requires only public imagery to support time-sensitive land management workflows. [ABSTRACT FROM AUTHOR]

Aquatic vegetation is an important component of aquatic ecosystems; therefore, the classification and mapping of aquatic vegetation is an important aspect of lake management. Currently, the decision tree (DT) classification method based on spectral indices has been widely used in the extraction of aquatic vegetation data, but the disadvantage of this method is that it is difficult to fix the threshold value, which, in turn, affects the automatic classification effect. In this study, Sentinel-2 MSI data were used to produce a sample set (about 930 samples) of aquatic vegetation in four inland lakes (Lake Taihu, Lake Caohai, Lake Honghu, and Lake Dongtinghu) using the visual interpretation method, including emergent, floating-leaved, and submerged vegetation. Based on this sample set, a DL model (Res-U-Net) was used to train an automatic aquatic vegetation extraction model. The DL model achieved a higher overall accuracy, relevant error, and kappa coefficient (90%, 8.18%, and 0.86, respectively) compared to the DT method (79%, 23.07%, and 0.77) and random forest (78%,10.62% and 0.77) when utilizing visual interpretation results as the ground truth. When utilizing measured point data as the ground truth, the DL model exhibited accuracies of 59%, 78%, and 91% for submerged, floating-leaved, and emergent vegetation, respectively. In addition, the model still maintains good recognition in the presence of clouds with the influence of water bloom. When applying the model to Lake Honghu from January 2017 to October 2023, the obtained temporal variation patterns in the aquatic vegetation were consistent with other studies. The study in this paper shows that the proposed DL model has good application potential for extracting aquatic vegetation data. [ABSTRACT FROM AUTHOR]

Controlling groundwater table decline could mitigate land subsidence and induced environmental hazards in over-explored areas. Nevertheless, this becomes a challenge in the multi-layered porous system as (in)elastic deformation simultaneously occurs due to vast spatiotemporal variability in the groundwater table. In this study, SBAS-InSAR was used to estimate annual land deformation during 2017–2022 in a specific region of North China Plain, in which aquifers are composed of many layers of fine-grained compressible sediments and the groundwater table has experienced a prolonged decline. The random forest (RF) was applied to establish the nonlinear relationship between accumulated deformation and its potential driving factors, including the depth to the groundwater table (GWD) and its change rate, and the compressible sediment thickness. Results show that the marked subsidence and uplift co-exist in the region even though the groundwater table has risen widely since the South–North Water Diversion Project. The land subsidence is attributed to inelastic compaction of the thick compressible deposits in depression cone centers, where the GWD is over 40 m and 90 m in the shallow and deep aquifers, respectively. In contrast, the marked uplift is primarily attributed to fast rising of the groundwater table (e.g., −2.44 m/a). The RF predictions suggest that, to control the subsidence, the GWD should be less than 20 and 70 m in the shallow and deep aquifers, respectively, and the rising rate of the GWD should increase to 2–5 times of current rates in the depression cones. To mitigate the marked uplift, the rising rate of the GWD should reduce to 1/2–1/5 of the current rates in the shallow aquifers. The uneven deformations of sediments in the depression cone centers and uplift in their boundaries may exacerbate geohazards. Therefore, it is vital to implement appropriate governance of groundwater recovery in the multi-layered porous system. [ABSTRACT FROM AUTHOR]

Soil particle size fractions (PSFs) are important properties for understanding the physical and chemical processes in soil systems. Knowledge about the distribution of soil PSFs is critical for sustainable soil management. Although log-ratio transformations have been widely applied to soil PSFs prediction, the statistical distribution of original data and the transformed data given by log-ratio transformations is different, resulting in biased estimates of soil PSFs. Therefore, multivariate random forest (MRF) was utilized for the simultaneous prediction of soil PSFs, as it is able to capture dependencies and internal relations among the three components. Specifically, 243 soil samples collected across the Loess Plateau were used. Meanwhile, Landsat data, terrain attributes, and climatic variables were employed as environmental variables for spatial prediction of soil PSFs. The results depicted that MRF gave satisfactory soil PSF prediction performance, where the R2 values were 0.62, 0.53, and 0.73 for sand, silt, and clay, respectively. Among the environmental variables, nighttime land surface temperature (LST_N) presented the highest importance in predicting soil PSFs in the Loess Plateau, China. Maps of soil PSFs and texture were generated at a 30 m resolution, which can be utilized as alternative data for soil erosion management and ecosystem conservation. [ABSTRACT FROM AUTHOR]

Brazil is the largest producer and exporter of coffee beans in the world. Given this relevance, it is important to monitor the crop to prevent attacks by pests. This study aimed to detect leaf miner (Leucoptera coffeella) infestation in a newly planted crop based on vegetation indices (VI) derived from aerial images obtained by a multispectral camera embedded in a remotely piloted aircraft (RPA) using random forest (RF). The study was conducted on the Cafua farm in the municipality of Lavras in southern Minas Gerais. The images were collected using a multispectral camera attached to a remotely piloted aircraft (RPA). Collections were carried out on 30 July 2019 (infested crop) and 16 December 2019 (post chemical control). The RF package in R software was used to classify the infested and healthy plants. The t test revealed significant differences in band means between healthy and infested plants, favouring higher means in healthy plants. VI also exhibited significant differences, with EXR being higher in infested plants and GNDVI, GOSAVI, GRRI, MPRI, NDI, NDRE, NDVI and SAVI showing higher averages in healthy plants, indicating distinct spectral responses and light absorption patterns between the two states of the plant. Due to the spectral differences between the classes, it was possible to classify the infested and healthy plants, and the RF algorithm performed very well. [ABSTRACT FROM AUTHOR]

Using the SWAN (Severe Weather Automatic Nowcasting) maximum reflectivity mosaic product and the lightning positioning observations (LPOs) from the ADTD (Advanced Direction and Time of Arrival Detection) system obtained during the 2018–2020 warm season (May to September), adding multi-characteristic LPO parameters in addition to lightning density, the retrieval relationship between lightning and maximum proxy reflectivity, deemed FRST, is constructed by using random forest. The FRST is compared with two empirical relationships from the GSI (Gridpoint Statistical Interpolation) assimilation system, and the results show that the FRST retrieved result better reflects the frequency distribution structure and peak interval of maximum reflectivity. The correlation coefficient between the FRST retrieved result and the observed maximum reflectivity is 0.7037, which is 3.38 (3.12) times greater than that of empirical GSI relationships. The root mean square error and the mean absolute error are 50.85% (28.05%) and 57.15% (35.19%) lower than those for the empirical GSI relationships, respectively. The equitable threat score (ETS) and bias score (BIAS) for FRST are better than those of the empirical GSI relationships in all three maximum reflectivity intervals. [ABSTRACT FROM AUTHOR]

High-resolution remote sensing image-based vegetation monitoring is a hot topic in remote sensing technology and applications. However, when facing large-scale monitoring across different sensors in broad areas, the current methods suffer from fragmentation and weak generalization capabilities. To address this issue, this paper proposes a multisource high-resolution remote sensing image-based vegetation extraction method that considers the comprehensive perception of multiple features. First, this method utilizes a random forest model to perform feature selection for the vegetation index, selecting an index that enhances the otherness between vegetation and other land features. Based on this, a multifeature synthesis perception convolutional network (MSCIN) is constructed, which enhances the extraction of multiscale feature information, global information interaction, and feature cross-fusion. The MSCIN network simultaneously constructs dual-branch parallel networks for spectral features and vegetation index features, strengthening multiscale feature extraction while reducing the loss of detailed features by simplifying the dense connection module. Furthermore, to facilitate global information interaction between the original spectral information and vegetation index features, a dual-path multihead cross-attention fusion module is designed. This module enhances the differentiation of vegetation from other land features and improves the network's generalization performance, enabling vegetation extraction from multisource high-resolution remote sensing data. To validate the effectiveness of this method, we randomly selected six test areas within Anhui Province and compared the results with three different data sources and other typical methods (NDVI, RFC, OCBDL, and HRNet). The results demonstrate that the MSCIN method proposed in this paper, under the premise of using only GF2 satellite images as samples, exhibits robust accuracy in extraction results across different sensors. It overcomes the rapid degradation of accuracy observed in other methods with various sensors and addresses issues such as internal fragmentation, false positives, and false negatives caused by sample generalization and image diversity. [ABSTRACT FROM AUTHOR]

The assessment of solar resources involves the utilization of physical or satellite models for the determination of solar radiation on the Earth's surface. However, a critical aspect of model validation necessitates comparisons against ground-truth measurements obtained from surface radiometers. Given the inherent challenges associated with establishing and maintaining solar radiation measurement networks—characterized by their expense, logistical complexities, limited station availability and the imperative consideration of climatic criteria for siting—countries endowed with substantial climatic diversity face difficulties in station placement. In this investigation, the measurements of annual solar irradiation, from meteorological stations of the National Weather Service in Mexico, were compared in different regions clustered by similarities in altitude, TL Linke, albedo and cloudiness index derived from satellite images; the main objective is to find the best ratio of annual solar irradiation in a set of clusters. Employing machine learning algorithms, this research endeavors to identify the most suitable model for predicting the ratio of annual solar irradiation and to determine the optimal number of clusters. The findings underscore the efficacy of the L-method as a robust technique for regionalization. Notably, the cloudiness index emerges as a pivotal feature, with the Random Forest algorithm yielding superior performance with a R2 score of 0.94, clustering Mexico into 17 regions. [ABSTRACT FROM AUTHOR]

Improved agricultural production systems, together with increased grain yield, are essential to feed the growing global population in the 21st century. Global gridded crop models (GGCMs) have been extensively used to assess crop production and yield simulation on a large geographical scale. However, GGCMs are less effective when they are used on a finer scale, significantly limiting the precision in capturing the yearly maize yield. To address this issue, we propose a relatively more advanced approach that downsizes GGCMs by combining machine learning and crop modeling to enhance the accuracy of maize yield simulations on a regional scale. In this study, we combined the random forest algorithm with multiple data sources, trained the algorithm on low-resolution maize yield simulations from GGCMs, and applied it to a finer spatial resolution on a regional scale in China. We evaluated the performance of the eight GGCMs by utilizing a total of 1046 county-level maize yield data available over a 30-year period (1980–2010). Our findings reveal that the downscaled models created for maize yield simulations exhibited a remarkable level of accuracy (R2 ≥ 0.9, MAE < 0.5 t/ha, RMSE < 0.75 t/ha). The original GGCMs performed poorly in simulating county-level maize yields in China, and the improved GGCMs in our study captured an additional 17% variability in the county-level maize yields in China. Additionally, by optimizing nitrogen management strategies, we identified an average maize yield gap at the county level in China ranging from 0.47 to 1.82 t/ha, with the south maize region exhibiting the highest yield gap. Our study demonstrates the high effectiveness of machine learning methods for the spatial downscaling of crop models, significantly improving GGCMs' performance in county-level maize yield simulations. [ABSTRACT FROM AUTHOR]

Generating orchards spatial distribution maps within a heterogeneous landscape is challenging and requires fine spatial and temporal resolution images. This study examines the effectiveness of Sentinel-1 (S1) and Sentinel-2 (S2) satellite data of relatively high spatial and temporal resolutions for discriminating major orchards in the Khairpur district of the Sindh province, Pakistan using machine learning methods such as random forest (RF) and a support vector machine. A Multicollinearity test (MCT) was performed among the multi-temporal S1 and S2 variables to remove those with high correlations. Six different feature combination schemes were tested, with the fusion of multi-temporal S1 and S2 (scheme-6) outperforming all other combination schemes. The spectral separability between orchards pairs was assessed using Jeffries-Matusita (JM) distance, revealing that orchard pairs were completely separable in the multi-temporal fusion of both sensors, especially the indistinguishable pair of dates-mango. The performance difference between RF and SVM was not significant, SVM showed a slightly higher accuracy, except for scheme-4 where RF performed better. This study concludes that multi-temporal fusion of S1 and S2 data, coupled with robust ML methods, offers a reliable approach for orchard classification. Prospectively, these findings will be helpful for orchard monitoring, improvement of yield estimation and precision based agricultural practices. [ABSTRACT FROM AUTHOR]

The presence of deep convective clouds is directly related to potential convective hazards, such as lightning strikes, hail, severe storms, flash floods, and tornadoes. On the other hand, Mexico has a limited and heterogeneous network of instruments that allow for efficient and reliable monitoring and forecasting of such events. In this study, a quasi-real-time framework for deep convective cloud identification and modeling based on machine learning (ML) models was developed. Eight different ML models and model assembly approaches were fed with Interest Fields estimated from Advanced Baseline Imager (ABI) sensor data on the Geostationary Operational Environmental Satellite-R Series (GOES-R) for one region in central Mexico and another in northeastern Mexico, both selected for their intense convective activity and high levels of vulnerability to severe weather. The results indicate that a simple approach such as Logistic Regression (LR) or Random Forest (RF) can be a good alternative for the identification and simulation of deep convective clouds in both study areas, with a probability of detection of (POD) ≈ 0.84 for Los Mochis and POD of ≈ 0.72 for Mexico City. Similarly, the false alarm ratio (FAR) ≈ 0.2 and FAR ≈ 0.4 values were obtained for Los Mochis and Mexico City, respectively. Finally, a post-processing filter based on lightning incidence (Lightning Filter) was applied with data from the Geostationary Lightning Mapper (GLM) of the GOES-16 satellite, showed great potential to improve the probability of detection (POD) of the ML models. This work sets a precedent for the implementation of an early-warning system for hazards associated with intense convective activity in Mexico. [ABSTRACT FROM AUTHOR]

The integration of optical and SAR datasets through ensemble machine learning models shows promising results in urban remote sensing applications. The integration of multi-sensor datasets enhances the accuracy of information extraction. This research presents a comparison of two ensemble machine learning classifiers (random forest and extreme gradient boost (XGBoost)) classifiers using an integration of optical and SAR features and simple layer stacking (SLS) techniques. Therefore, Sentinel-1 (SAR) and Landsat 8 (optical) datasets were used with SAR textures and enhanced modified indices to extract features for the year 2023. The classification process utilized two machine learning algorithms, random forest and XGBoost, for urban impervious surface extraction. The study focused on three significant East Asian cities with diverse urban dynamics: Jakarta, Manila, and Seoul. This research proposed a novel index called the Normalized Blue Water Index (NBWI), which distinguishes water from other features and was utilized as an optical feature. Results showed an overall accuracy of 81% for UIS classification using XGBoost and 77% with RF while classifying land use land cover into four major classes (water, vegetation, bare soil, and urban impervious). However, the proposed framework with the XGBoost classifier outperformed the RF algorithm and Dynamic World (DW) data product and comparatively showed higher classification accuracy. Still, all three results show poor separability with bare soil class compared to ground truth data. XGBoost outperformed random forest and Dynamic World in classification accuracy, highlighting its potential use in urban remote sensing applications. [ABSTRACT FROM AUTHOR]

Since the early 1950s, the development of human settlements and over-exploitation of agriculture in the China side of the Amur River Basin (CARB) have had a major impact on the water environment of the surrounding lakes, resulting in a decrease of aquatic vegetation. According to the United Nations Sustainable Development Goals, a comprehensive understanding of the extent and variability of aquatic vegetation is crucial for preserving the structure and functionality of stable aquatic ecosystems. Currently, there is a deficiency in the CARB long-sequence dataset of aquatic vegetation distribution in China. This shortage hampers effective support for actual management. Therefore, the development of a fast, robust, and automatic method for accurate extraction of aquatic vegetation becomes crucial for large-scale applications. Our objective is to gather information on the spatial and temporal distribution as well as changes in aquatic vegetation within the CARB. Utilizing a hybrid approach that combines the maximum spectral index composite and Otsu algorithm, along with the integration of convolutional neural networks (CNN) and random forest, we applied this methodology to obtain an annual dataset of aquatic vegetation spanning from 1985 to 2020 using Landsat series imagery. The accuracy of this method was validated through both field investigations and Google Images. Upon assessing the confusion matrix spanning from 1985 to 2020, the producer accuracy for aquatic vegetation classification consistently exceeded 87%. Further quantitative analysis unveiled a discernible decreasing trend in both the water and vegetation areas of lakes larger than 20 km2 within the CARB over the past 36 years. Specifically, the total water area decreased from 3575 km2 to 3412 km2, while the vegetation area decreased from 745 km2 to 687 km2. These changes may be attributed to a combination of climate change and human activities. These quantitative data hold significant practical implications for establishing a scientific restoration path for lake aquatic vegetation. They are particularly valuable for constructing the historical background and reference indices of aquatic vegetation. [ABSTRACT FROM AUTHOR]

Complex-terrain clutter presents serious nonuniformity, which has a significant impact on radar target detection, communication, and navigation. The accurate acquisition of the clutter characteristics by measurement or calculation for large and complex terrains has always posed a challenge due to the high costs of the measurement, as well as the intricate and diverse environmental factors. To address this challenge, we proposed a research methodology that leverages the similarity of multidimensional terrain features to infer the clutter characteristics of unmeasured regions, particularly those that are difficult or impossible to measure directly. In order to realize this study object, we constructed a dataset consisting of multidimensional environmental and clutter data to quantitatively characterize the complex environmental information in a vast territory. Within the dataset, we selected two regions with similar terrain characteristics: one region served as the source data for mining and analyzing features, while the other was designated as the target data region for method validation. Through the application of prior-knowledge-based classification and multifactor weight analysis on the dataset, two novel estimation techniques were devised. The first method, designated as PCKRF, blended prior-knowledge classification, weighted K-means clustering, and the random forest (RF) algorithm; and the second method, labeled PCKMW, integrated prior-knowledge classification, weighted K-means clustering, and the minimum weighted distance (MW) approach. In estimating and validating the clutter data from the source region to the target region, the performances of both the PCKRF and PCKMW methods were notably superior to those of the RF, MW, and K-means minimum weighting (KMW). Specifically, the root-mean-squared error (RMSE) was enhanced from a range of 7 dB–10 dB to a range of 4 dB–6 dB, while the determination coefficient (R2) was increased from a range of −1.15–0.09 to a range of 0.25–0.66. The above demonstration illustrates that the current achievements in the clutter estimation methods offer a viable option for accurately recognizing clutter characteristics in complex-terrain environments where comprehensive data collection may be difficult or impossible, with lower human and economic costs. [ABSTRACT FROM AUTHOR]

Indoor 3D reconstruction is particularly challenging due to complex scene structures involving object occlusion and overlap. This paper presents a hybrid indoor reconstruction method that segments the room point cloud into internal and external components, and then reconstructs the room shape and the indoor objects in different ways. We segment the room point cloud into internal and external points based on the assumption that the room shapes are composed of some large external planar structures. For the external, we seek for an appropriate combination of intersecting faces to obtain a lightweight polygonal surface model. For the internal, we define a set of features extracted from the internal points and train a classification model based on random forests to recognize and separate indoor objects. Then, the corresponding computer aided design (CAD) models are placed in the target positions of the indoor objects, converting the reconstruction into a model fitting problem. Finally, the indoor objects and room shapes are combined to generate a complete 3D indoor model. The effectiveness of this method is evaluated on point clouds from different indoor scenes with an average fitting error of about 0.11 m, and the performance is validated by extensive comparisons with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The application of lidar data to assist with forest inventory is common around the world. However, the determination of tree species is still somewhat elusive. Lidar data collected using UAS (uncrewed aircraft systems) platforms offer high density point cloud data for areas from a few to several hundred hectares. General point cloud metrics computed using these data captured differences in the crown structure that proved useful for species classification. For our study, we manually adjusted plot and tree locations to align field trees and UAS lidar point data and computed common descriptive metrics using a small cylindrical sample of points designed to capture the top three meters and leader of each tree. These metrics were used to train a random forest classifier to differentiate between two conifer species, Douglas fir and western hemlock, common in the Pacific Northwest region of the United States. Our UAS lidar data had a single swath pulse density of 90 pulses/m2 and an aggregate pulse density of 556 pulses/m2. We trained classification models using both height and intensity metrics, height metrics alone, intensity metrics alone, and a small subset of five metrics, and achieved overall accuracies of 91.8%, 88.7%, 78.6%, and 91.5%, respectively. Overall, we showed that UAS lidar data captured morphological differences between the upper crowns of our two target species and produced a classification model that could be applied over large areas. [ABSTRACT FROM AUTHOR]

Surface urban heat islands (SUHIs) can extend beyond the urban boundaries and greatly affect the thermal environment of continuous regions over an agglomeration. Traditional urban-rural dichotomy depending on the built-up and non-urban lands is challenged in characterizing regional SUHIs, such as how to accurately quantify the intensity, spatial pattern, and scales of SUHIs, which are vulnerable to SUHIs, and what the optimal scale for conducting measures to mitigate the SUHIs. We propose a machine-learning-assisted solution to address these problems based on the thermal similarity in the Yangtze River Delta of China. We first identified the regional-level SUHI zone of approximately 42,328 km2 and 38,884 km2 and the areas that have no SUHI effects from the annual cycle of land surface temperatures (LSTs) retrieved from Terra and Aqua satellites. Defining SUHI as an anomaly on background condition, random forest (RF) models were further adopted to fit the LSTs in the areas without the SUHI effects and estimate the LST background and SUHI intensity at each grid point in the SUHI zone. The RF models performed well in fitting rural LSTs with a simulation error of approximately 0.31 °C/0.44 °C for Terra/Aqua satellite data and showed a good generalization ability in estimating the urban LST background. The RF-estimated daytime Aqua/SUHI intensity peaked at approximately 6.20 °C in August, and the Terra/SUHI intensity had two peaks of approximately 3.18 and 3.81 °C in May and August, with summertime RF-estimated SUHIs being more reliable than other SUHI types owing to the smaller simulation error of less than 1.0 °C in July–September. This machine-learning-assisted solution identified an optimal SUHI scale of 30,636 km2 and a zone of approximately 23,631 km2 that is vulnerable to SUHIs, and it provided the SUHI intensity and statistical reliability for each grid point identified as being part of the SUHI. Urban planners and decision-makers can focus on the statistically reliable RF-estimated summertime intensities in SUHI zones that have an LST annual cycle similar to that of large cities in developing effective strategies for mitigating adverse SUHI effects. In addition, the selection of large cities might strongly affect the accuracy of identifying the SUHI zone, which is defined as the areas that have an LST annual cycle similar to large cities. Water bodies might reduce the RF performance in estimating the LST background over urban agglomerations. [ABSTRACT FROM AUTHOR]

Cocoa is the economic backbone of Côte d'Ivoire and Ghana, making them the leading cocoa-producing countries in the world. However, cocoa farming has been a major driver of deforestation and landscape degradation in West Africa. Various stakeholders are striving for a zero-deforestation cocoa sector by implementing sustainable farming strategies and a more transparent supply chain. In the context of tracking cocoa sources and contributing to cocoa-driven deforestation monitoring, the demand for accurate and up-to-date maps of cocoa plantations is increasing. Yet, access to limited reference data and imperfect data quality can impose challenges in producing reliable maps. This study classified full-sun-cocoa-growing areas using limited reference data relative to the large and heterogeneous study areas in Côte d'Ivoire and Ghana. A Sentinel-2 composite image of 2021 was generated to train a random forest model. We undertook reference data refinement, selection of the most important handcrafted features and data sampling to ensure spatial independence. After refining the quality of the reference data and despite their size reduction, the random forest performance was improved, achieving an overall accuracy of 85.1 ± 2.0% and an F1 score of 84.6 ± 2.4% (mean ± one standard deviation from ten bootstrapping iterations). Emphasis was given to the qualitative visual assessment of the map using very high-resolution images, which revealed cases of strong and weak generalisation capacity of the random forest. Further insight was gained from the comparative analysis of our map with two previous cocoa classification studies. Implications of the use of cocoa maps for reporting were discussed. [ABSTRACT FROM AUTHOR]

The goal of this study was to estimate the areas under willow cultivation by farmers, as well as their growth and health status. Due to the extremely small patch size of land cover types in the study area, Sentinel-2 data were used to conduct supervised classification based on the random forest machine learning technique, and a large training dataset was produced from PlanetScope satellite imagery. The results of image classification using Google Earth Engine indicated that the Sentinel data were suitable for identifying willow-cultivated areas. It was found that these areas declined from 875.32 ha in 2017 to 288.41 ha in 2022. The analysis of the growth and health conditions of willow-cultivated plots also revealed that the temporal variations in the NDVI in these plots decreased significantly in 2022 as compared to previous years (p < 0.05). An in-depth analysis revealed a significant positive correlation between NDVI, precipitation, and temperature. It was found that the most efficient components explaining the process of browning the vegetation in the planted willow plots were the increasing temperature and decreasing precipitation. This research may be used to document the national and global monitoring efforts for climate change adaptation. [ABSTRACT FROM AUTHOR]

Sea ice motion (SIM) plays a crucial role in setting the distribution of the ice cover in the Arctic. Limited by images' spatial resolution and tracking algorithms, challenges exist in obtaining coastal sea ice motion (SIM) based on passive microwave satellite sensors. In this study, we developed a method based on random forest (RF) models to obtain Arctic SIM in winter by incorporating wind field and coastal geographic location information. These random forest models were trained using Synthetic Aperture Radar (SAR) SIM data. Our results show good consistency with SIM data retrieved from satellite imagery and buoy observations. With respect to the SAR data, compared with SIM estimated with RF model training using reanalysis surface wind, the results by additional coastal information input had a lower root mean square error (RMSE) and a higher correlation coefficient by 31% and 14% relative improvement, respectively. The latter SIM result also showed a better performance for magnitude, especially within 100 km of the coastline in the north of the Canadian Arctic Archipelago. In addition, the influence of coastline on SIM is quantified through variable importance calculation, at 22% and 28% importance of all RF variables for east and north SIM components, respectively. These results indicate the great potential of RF models for estimating SIM over the whole Arctic Ocean in winter. [ABSTRACT FROM AUTHOR]

The mapping of invasive plant species is essential for effective ecosystem control and planning, especially in protected areas. One of the widespread invasive plants that threatens the species richness of Natura 2000 habitats in Europe is the large-leaved lupine (Lupinus polyphyllus). In our study, this species was identified at two Natura 2000 sites in southern Poland using airborne HySpex hyperspectral images, and support vector machine (SVM) and random forest (RF) classifiers. Aerial and field campaigns were conducted three times during the 2016 growing season (May, August, and September). An iterative accuracy assessment was performed, and the influence of the number of minimum noise fraction (MNF) bands on the obtained accuracy of lupine identification was analyzed. The highest accuracies were obtained for the August campaign using 30 MNF bands as input data (median F1 score for lupine was 0.82–0.85), with lower accuracies for the May (F1 score: 0.77–0.81) and September (F1 score: 0.78–0.80) campaigns. The use of more than 30 MNF bands did not significantly increase the classification accuracy. The SVM and RF algorithms allowed us to obtain comparable results in both research areas (OA: 89–94%). The method of the multiple classification and thresholding of frequency images allowed the results of many predictions to be included in the final map. [ABSTRACT FROM AUTHOR]

We present an evaluation of different deep learning and machine learning approaches for tree health classification in the Black Forest, the Harz Mountains, and the Göttinger Forest on a unique, highly accurate tree-level dataset. The multispectral UAV data were collected from eight forest plots with diverse tree species, mostly conifers. As ground truth data (GTD), nearly 1500 tree polygons with related attribute information on the health status of the trees were used. This data were collected during extensive fieldwork using a mobile application and subsequent individual tree segmentation. Extensive preprocessing included normalization, NDVI calculations, data augmentation to deal with the underrepresented classes, and splitting the data into training, validation, and test sets. We conducted several experiments using a classical machine learning approach (random forests), as well as different convolutional neural networks (CNNs)—ResNet50, ResNet101, VGG16, and Inception-v3—on different datasets and classes to evaluate the potential of these algorithms for tree health classification. Our first experiment was a binary classifier of healthy and damaged trees, which did not consider the degree of damage or tree species. The best results of a 0.99 test accuracy and an F1 score of 0.99 were obtained with ResNet50 on four band composites using the red, green, blue, and infrared bands (RGBI images), while VGG16 had the worst performance, with an F1 score of only 0.78. In a second experiment, we also distinguished between coniferous and deciduous trees. The F1 scores ranged from 0.62 to 0.99, with the highest results obtained using ResNet101 on derived vegetation indices using the red edge band of the camera (NDVIre images). Finally, in a third experiment, we aimed at evaluating the degree of damage: healthy, slightly damaged, and medium or heavily damaged trees. Again, ResNet101 had the best performance, this time on RGBI images with a test accuracy of 0.98 and an average F1 score of 0.97. These results highlight the potential of CNNs to handle high-resolution multispectral UAV data for the early detection of damaged trees when good training data are available. [ABSTRACT FROM AUTHOR]