Search

Secondary metabolites have high ecological and economic values. Measuring the amounts of these metabolites in plants through laboratory analysis is time-consuming and expensive. On the other hand, the laboratory results cannot be generalized to a wide area of rangelands with diverse climates, topography, and soil. Therefore, the present study aims to evaluate the potential of PRISMA hyperspectral data to estimate the rangeland phenol concentration at landscape scale in western Isfahan province, Iran. Phenol concentration and spectral signatures were extracted from 42 plant individuals, including Astragalus adscendens, Astragalus verus, Daphne mucronata, Anabasis aphylla, and Phlomis olivieri using laboratory methods and spectroscopy in the range of 350 to 2500 nm. Phenol-sensitive bands were identified by establishing a relationship between phenol concentration and all spectral bands by the Partial Least Square Regression (PLSR) method. The map of phenol spatial changes was then produced with the Bayesian Regularized Artificial Neural Network Model (BRNN), Random Forest (RF), Generalized Linear Model (GAM), Generalized Additive Model (GLM), and Gaussian Process Regression (GPR) in rangelands. The results showed that the phenol concentration in different individuals was between 3.65 and 20.13 (mgGAE/gDW), and species spectral absorptions ranged from 1.650 to 1.660. The very high coefficient of determination of phenol concentration with spectral data (R2 = 0.94) confirmed the use of these data in phenol mapping at the landscape scale. The maximum estimated phenol concentration by GLM, GAM, RF, BRNN, and GPR models was 36.40, 26.76, 18.07, 22.74, and 32.92 GAE/g DW, respectively; which RF model had the highest (R2 = 0.955) and GLM had the lowest accuracy (R2 = 0.816). The findings show that hyperspectral data can estimate secondary metabolites at the landscape scale and can supplement laboratory methods in managing rangeland plants. [ABSTRACT FROM AUTHOR]

Machine learning can offer an efficient method to identify and map caves, sinkholes, and other cave-like features (i.e. sinkholes, rockshelters, voids) using remotely sensed imagery. While there exists a body of work applying machine learning for sinkhole identification, little work exists for caves. In the densely forested and rugged Maya Lowlands, developing such a methodology can help archaeologists to identify previously unknown caves that may contain important archaeological materials. Here, we introduce a proof-of-concept project that uses random forest and lidar-derived landscape morphometrics to map caves and other cave-like features in northwest Belize. Several undocumented caves and cave-like features were identified in our study area based on model results. Next steps towards making a more robust version of this model include the addition of more training data and integration of a larger number of morphologic parameters. Based on the results described here as well as those in cited works focused on caves, we proposed machine learning as a first step in cave and cave-like feature identification, followed then by fieldwork and ground-truthing. [ABSTRACT FROM AUTHOR]

This study presents a novel Spectral Triad feature selection (STfs) technique based on music theory and compares it to the entire Sentinel-2 feature space and Random Forest-Recursive Feature Elimination (RF-RFE). The optimal subsets were evaluated with Random Forest for retrieving Leaf Area Index (LAI), Leaf Chlorophyll Content (LCab), and Canopy Chlorophyll Content (CCC) in a semi-arid agricultural landscape. The results indicated that the proposed STfs algorithm obtained equivalent or better (i.e. by 1 - 3%) retrieval accuracies for LAI (R2 cv of 66%, root mean squared error of cross-validation [RMSEcv] of 0.53 m2 m-2), LCab (R2 cv: 74%, RMSEcv: 7.09 mg cm-2) and CCC (R2 cv: 77%, RMSEcv: 33.69 mg cm-2), using only 5, 7 and 7 variables, respectively, when compared to RF-RFE and entire Sentinel-2 feature space. Overall, the proposed STfs algorithm has great potential to optimize the spectral feature space of quasi-hyperspectral sensors for rapid crop biophysical and biochemical parameter retrieval. [ABSTRACT FROM AUTHOR]

Precise estimation of Sea Surface Salinity (SSS) is of prime importance to know marine physical and biochemical processes. In this manuscript we have utilized the Random Forest (RF) and Support Vector Regression (SVR) to estimate the SSS concentration. Particularly, we have utilized the global SSS values provided by the Copernicus Marine Services. We have also extracted the Aqua MODIS and Sentinel-3 data from the Google Earth Engine platform. The complete range of SSS varies approximately from 6 psu to 38 psu which enables the global application of the dataset. We have also studied the importance of different wavelength bands and their significance to SSS using the RF model. It is found that wavelengths around 400 nm have their highest significance due to the sensitiveness to Chromophoric Dissolved Organic Matter (CDOM) and other related constituents. For the regression analysis we have also utilized the Laplacian kernel in the SVR. It is found that the SVR with Laplace kernel outperforms the RF and SVR with Radial Basis Function (RBF) kernel. The trained algorithms are used to estimate the SSS content over the Bay of Bengal and the Arabian Sea regions which show interesting variations in SSS content due to diverse climatological conditions. [ABSTRACT FROM AUTHOR]

Urban agriculture continues to play a key role in addressing food insecurity and poverty across developing countries. This study used Landsat 5 imagery to map the spatial and temporal distribution of cropland in Harare Metropolitan in Zimbabwe using the Random Forest classifier in Google Earth Engine. Results show that the area under cultivation fluctuated considerably between 1985 and 2019 and several factors account for this trend. The results of this study illustrate the increasing importance of remote sensing in assessing cropland in urban areas that provides insights into the contribution of urban agriculture to food security. [ABSTRACT FROM AUTHOR]

Quickly and accurately obtaining information on rice planting areas is crucial for maintaining food security and social stability. Based on the time series of Sentinel-1A images, this study proposes an automatic rice mapping method called the Dynamic Threshold Time-Weighted Dynamic Time Warping method (DT-TWDTW). This method consists of two parts. First, rice samples are extracted automatically by a dynamic threshold method based on the unique flooding signal before and after rice transplanting. Then, the Time-Weighted Dynamic Time Warping (TWDTW) method is used for rice mapping based on the cumulative cost matrix between unknown pixels and rice samples. The results show that the DT-TWDTW method can achieve satisfactory mapping accuracy with an overall accuracy of 94.6%, higher than random forest (89.9%), and support vector machine (91.7%). This study provides a new approach and perspective for remote sensing monitoring of rice, especially for some regions without prior phenological knowledge and collection of the rice samples. [ABSTRACT FROM AUTHOR]

Efficiently obtaining tobacco planting area is significant for rationally allocating tobacco resources and realizing the balance between supply and demand. However, tobacco fields are characterized by fragmentation in hilly areas, which brings various challenges to extracting the tobacco planting area. A 16-square-kilometre tobacco planting region in Xuancheng City, Anhui Province, China, was selected as the study area in this paper. First, the single-temporal full-feature sets (STFFS), a time-series full-feature set (TFFS) and a time-series optimal-feature set (TOFS) were constructed from multi-period Sentinel-2 images, respectively. Then, we applied Random Forest (RF), Support Vector Machine (SVM), Neural Network Classification (NNC) and Maximum Likelihood Classification (MLC) to classify the feature sets and compare the classification accuracy. The experimental results demonstrate that: (1) The best growth stage of tobacco remote sensing recognition is the mulching film phase of the spherical plant stage (ST1 period). (2) The classification accuracy indicates that TOFS outperforms the STFFS. (3) TOFS can still maintain the same classification accuracy as TFFS with fewer feature dimensions. (4) The RF classifier has great stability and robustness, which achieve an overall accuracy (OA) of 90.65%, 93.50%, and 93.09% based on the feature sets of ST1 period, TFFS, and TOFS, respectively. [ABSTRACT FROM AUTHOR]

Rot in commercial timber reduces the value of the wood substantially and estimating the occurrence, severity, and volume of heartwood rot would be a useful tool in decision-making to minimize economic losses. Remotely sensed data has recently been used for mapping rot on a single-tree level, and although the results have been relatively poor, some potential has been shown. This study applied area-based approaches to predict rot occurrence, rot severity, and rot volume , at an area level. Ground reference data were collected from harvester operations in 2019–2021. Predictor variables were calculated from multi-temporal remotely sensed data together with environmental variables. Response variables from the harvester data and predictor variables from remotely sensed data were aggregated to grid cells and to forest stands. Random Forest models were built for the different combinations of response variables and predictor subsets, and validated with both random- and spatial cross-validation. The results showed that it was not possible to estimate rot occurrence and rot severity with the applied modeling procedure (pR2: 0.00–0.16), without spatially close training data. The better performance of rot volume models (pR2: 0.12–0.37) was mainly due to the correlation between timber volume and rot volume. [ABSTRACT FROM AUTHOR]

Coastal dunes are considered some of the most threatened and vulnerable habitats in the European Union. Mapping the spatial distribution of these habitats is an essential task for their conservation. Advances in Unoccupied Aerial Vehicles (UAVs) facilitate the flexible acquisition of high-resolution imagery for identifying detailed spatial distributions of habitats within dune systems. This study aimed to assess the effectiveness of UAV remote sensing for mapping these habitat types. Specifically, we determined the impact of temporally acquired UAV-derived spectral and topographic information on classification accuracy. The work combined the multi-temporal UAV imagery with field observation data and used the Random Forest machine learning algorithm to classify dune habitats. Results showed that using multi-temporal UAV imagery increased classification accuracy compared to using uni-temporal UAV imagery (92.37% vs. 84.09%, respectively). Also, including topographic information consistently improved accuracy, regardless of the number of image sets used (the highest accuracy increased from 84.81% to 92.57% for a uni-temporal model). Temporal analyses showed that the data acquired in the middle period of the growing season were better than those acquired in the early or late periods. The methodology presented here demonstrates the potential of using UAV data for detailed mapping and monitoring of habitat types. [ABSTRACT FROM AUTHOR]

Land cover (LC) classification remains a challenging task due to the diversity of terrain and topography, limited prior knowledge, and complex data sets. These variations can lead to differences in illumination and shading, which can affect the appearance of objects in the image. The local binary pattern (LBP) model is an effective technique for capturing local texture information in an image, which can help to overcome the effects of topography diversity by analysing patterns in different image regions, even if the illumination or shading conditions are different. However, LBP alone is inadequate for characterizing high-resolution remotely sensed images with complex semantic content as it only utilizes sign information in the local region. In this paper, a new texture characterization descriptor, known as completed homogeneous LBP (CHLBP), is proposed as an improved version of homogeneous LBP (HLBP) for LC classification of remotely sensed images. The CHLBP method mainly involves the following steps: first, sign and magnitude information from the HLBP descriptor is extracted, providing an effective alternative to the HLBP complementary contrast measure. Second, for each sign and magnitude function, a new splitting factor δ is used to obtain a depth relationship between the centre and its neighbouring pixels and to enhance noise robustness. Finally, the centre pixels representing the image grey level are also considered to contain discriminative information. The performance of our descriptor is evaluated using four challenging texture databases: Outex (TC10, TC12), Geofen Image Dataset (GID), and large-scale aerial (AID). Extensive experiments were performed using four classifiers: Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Random Forest (RF), and Multi-Layer Perceptron (MLP), demonstrating the effectiveness and robustness of our descriptor against noise and free noise conditions in public remote sensing datasets. [ABSTRACT FROM AUTHOR]

Mapping and monitoring disturbances in vegetation over large areas demand reliable approaches and accurate end-user maps. Methods and algorithms have been developed to meet satisfactory disturbance map accuracies, and the combination of multiple approaches has shown promise as a reliable alternative to any single method. However, extracting meaningful disturbance information from these combined methods is still challenging. Data variance from environmental conditions and disturbance drivers leads to spatial-temporal heterogeneity in land surfaces over large areas, which results in mapping errors. We evaluated the effectiveness of ensemble classification and data-driven regionalization for mapping vegetation disturbances at a broad scale. Using Google's Earth Engine cloud computing platform, our ensemble approach combines multispectral LandTrendr outputs reflecting preliminary disturbance information in a Random Forest model to map disturbances in Minas Gerais, Brazil. We then applied an unsupervised clustering technique to perform data-driven regionalization of our study area using several sources of environmental and anthropogenic information and analysed gains and losses in map accuracies. Our results indicated gains in accuracy by the ensemble method compared to non-ensemble methods of disturbance mapping, which ranged from 7.3 to 29.9% in overall accuracy at the 5% significance level. Data-driven regionalization addressed complexities arising from variability in vegetation types, local climate, and topography across our study area, identifying climate and seasonal metrics as important variables for reducing uncertainties in vegetation disturbance maps. The integration of these techniques has revealed significant potential for increasing map accuracy and has provided important insights into the development of disturbance mapping methods in heterogeneous environments. [ABSTRACT FROM AUTHOR]

Datasets containing recorded landslide and non-landslide samples can greatly influence the performance of machine learning (ML) models, which are commonly used in landslide susceptibility mapping (LSM). However, the non-landslide samples cannot be directly obtained. In this study, a pattern-based approach is proposed to improve the LSM process, constructing unsupervised machine learning (UML) – supervised machine learning (SML) collaborative models in which the non-landslide samples can be reasonably selected. Two UML models, the Gaussian mixture model (GMM) and K-means, are introduced to sample the non-landslide datasets with four sampling selections (abbreviated as A, B, C and D, respectively). Then non-landslide patterns recognised by the UML models are learned by the random forest (RF). A new sensitivity index, accuracy improvement ratio (AIR), is defined to evaluate the superiority of these sampling selections. Compared with the GMM-RF model, the K-means-RF model is more capable of recognising non-landslide patterns and providing sufficient and reliable non-landslide samples. The sampling selection A of the K-means-RF with an AIR value of 2.3 is regarded as the best selection. The results indicate that the UML-SML model based on the pattern-based approach offers an effective strategy to find the non-landslide samples and has a better solution to the LSM. [ABSTRACT FROM AUTHOR]

The quantification of grassland above-ground biomass (AGB) and grazing intensity (GI) and their distribution in space is of great significance to grassland management and eco-conservation. Remote-sensing technology is widely applied, but it is difficult to measure accurately when monitoring GI. In this study, the neural network, random forest and statistical function models of the relationship between Landsat NDVI and AGB were constructed by field survey and literature data collection in Inner Mongolia grassland, China. By comparing the accuracy among the three models, we constructed a remote-sensing retrieving model of grass AGB. We also estimated the grassland AGB during the peak growing season (August) for Inner Mongolia. Frequency histograms were then made to identify AGB thresholds under four GI levels (light or ungrazed, moderate grazing, overgrazing and extreme grazing) for each of three grassland types (meadow steppe, typical steppe and desert steppe). This study shows that the random forest model simulates grass AGB more accurately than other models. The spatial distribution of AGB in Inner Mongolia grasslands showed a tendency of decreasing from southeast to northwest, with an increasing trend in the last 10 years. The four GI levels in 2021 accounted for 18%, 25%, 36% and 21% of the grasslands in Inner Mongolia, respectively, and over the last 10 years the GI first improved and then deteriorated. This study provides a guideline to remote monitoring for grassland AGB and GI, and supplies scientific support for sustainable management and grassland restoration of large-scale grasslands. [ABSTRACT FROM AUTHOR]

The rapid expansion of exotic saltcedar along riparian corridors has dramatically altered the landscape structure and ecological function of riparian habitats in the western United States. The development of accurate and reproducible mapping methods with remote sensing plays an indispensable role in the timely monitoring of saltcedar, re-evaluating its ecological functions, and establishing effective control measures. The utmost challenge for achieving this goal is manifested as the lack of time series of remote sensing images to capture the saltcedar phenology adequately. To this end, the newly available Landsat 9 images, combined with its counterpart of Landsat 8, offer a precious opportunity to compensate for the temporal image shortage. To understand Landsat 9 in the saltcedar classification and to discover helpful information for its application, this study presents the first attempt to classify saltcedar using intra-annual Landsat 8 and Landsat 9 images. We adopted two machine learning algorithms, support vector machine (SVM) and random forest (RF), to compare the performance of Landsat 9 and Landsat 8 for intra-annual saltcedar classification. In addition, we investigated the respective contribution of each spectral band to the overall performance and identified the optimal time window for saltcedar classification. The results indicated that the difference in classification performance between Landsat 9 and Landsat 8 was insignificant. The shortwave infrared bands associated with both Landsat 8 & 9 have contributed most to the process of saltcedar identification. Image acquired in July, November, and December yielded better results than other months for saltcedar classification. It is concluded that Landsat 8 & 9 constellation has the potential to refine saltcedar classification accuracy on larger spatial and temporal scales. [ABSTRACT FROM AUTHOR]

Remote sensing and land resource surveys have been used in recent decades for land use/land cover (LULC) mapping; however, keeping the developed LULC up-to-date and consistent with land survey statistics remains challenging. This study developed a practical and effective framework to automatically update existing LULC products and bridge the gap between remote sensing classification results and land survey data. This study employed Landsat imagery time series, change detection algorithms, sample migration, and random forests to develop a framework for updating existing LULC products in China from 1980–2015 to 1980–2022. The updated LULC maps reflect the post-2015 LULC changes well and maintain continuity with the pre-2015 products. Additionally, a statistical space allocation method based on the minimum cross-entropy strategy was proposed to optimize the LULC maps, increasing the correlation coefficient (r) with China's second and third national land survey statistics from 0.41–0.89 to 0.86–0.99. Thus, the framework and products developed in this study provide valuable tools for sustainable land use and policy planning. [ABSTRACT FROM AUTHOR]

The extraction of large dam candidate regions is critical for broad-scale efforts to rapidly detect large-area dams. The framework proposed in this paper attempts to combine random forest classification models and spatial analysis methods with large dam candidate area extraction methods for large-scale areas. First, we studied the combination of optical, microwave, texture, and topographic features of the dam and constructed a multisource remote sensing and topographic feature vector of the dam. Secondly, we constructed random forest classifiers in different study areas and evaluate their performance. Then we explored the geographic characteristics of the dams and their relationships with other features. Finally, we introduced the spatial analysis method to constrain the large dam candidate area. The proposed framework was tested in a total area of 968,533 km2 in five countries and achieved promising results, which constrained the candidate area to less than 1.06% of the total area. We calculated the completeness rate of large dams using the multi-source dam datasets. The framework achieved a completeness rate of more than 97.62%. Our results show that the entire framework is reliable for automated and fast large dam candidate area acquisition based on data from open remote sensing products. [ABSTRACT FROM AUTHOR]

In this study, the authors propose a model, called the Daily Downward Shortwave Radiation Random Forest Model over Rugged Terrain (DSRMT), to accurately calculate the downward shortwave radiation over a terrain without bright surface on clear days at a daily scale (DSRdaily−rugged). It was built by using the random forest method based on the comprehensive samples from CERES4_SYN1deg_Ed4A within 17 typical mountainous regions. DSRMT could directly estimate DSRdaily-rugged from the instantaneous direct and diffuse solar radiation on a flat surface during 10:30–14:30hrs on each day by comparing with the terrain factors from a digital elevation model, broadband albedo from the Global Land Surface Satellite, and ancillary information. The in-situ validation results showed that it generally delivered superior performance in estimating DSRdaily-rugged at any time during 10:30–14:30hrs, especially at noon, yielding a validated root mean-squared error (RMSE) of 24.90–29.22 Wm−2 and mean absolute error (MAE) of 19.16–22.94 Wm−2, and the average weighted DSRdaily-rugged were usually more accurate with the RMSE and MAE of 21.63 and 17.14 Wm−2. Overall, DSRMT was found to deliver satisfactory performance because of its high accuracy, robustness, ease of implementation, and efficiency, so it has the strong potential to be widely used in practice. [ABSTRACT FROM AUTHOR]

Satellite images are widely used for crop yield estimation, but their coarse spatial resolution means that they often fail to provide detailed information at the field scale. Recently, a new generation of high-resolution satellites and CubeSat platforms has been launched. In this study, satellite data sources including PlanetScope and Sentinel-2 were combined with topographic and climatic variables, and the improvement in wheat yield estimation was evaluated. Wheat yield data from a combine harvester were used to train and validate a yield estimation model based on random forest regression. Nine vegetation indices (NDVI, GNDVI, MSAVI2, MTVI2, MTCI, reNDVI, SAVI, EVI and WDVI) and spectral bands were tested. During the model training, the Sentinel-2 data realized a slightly higher estimation accuracy than the PlanetScope data. However, combining environmental data with the PlanetScope data realized the highest estimation accuracy. For the validated models, adding the topographic and climatic datasets to the satellite data sources improved the estimation accuracy, and the results were slightly better with the Sentinel-2 data than with the PlanetScope data. Observation data of the milk and dough stages provided the highest estimation accuracy of the wheat yield at 210–225 days after sowing. [ABSTRACT FROM AUTHOR]

Groundwater contamination is a serious health problem affected by land use/land cover (LULC) changes. Therefore, this study aims to investigate the impacts of LULC on groundwater levels and quality in the Emirate of Abu Dhabi over the past two decades. Two sets of Landsat images were used to classify LULC using the random forest (RF) classifier, while an image-different tool was used to monitor changes in LULC from 2000 to 2020. After that, a spatial analysis was performed by comparing LULC maps against the hydrological maps. The results show a rapid increase in all LULC classes, whereas the groundwater level has depleted by 40 m. The results also show that the area of high-water quality across the study area was reduced by 479 km2 (0.79%). The results reveal significant hydrological changes in response to rapid urbanization. [ABSTRACT FROM AUTHOR]

The landscape-level estimation of nitrogen will constitute a significant input in global change models. High resolution broadband satellite technology is a promising solution to the limitation of spatial coverage. This study sought to identify an optimal spatial resolution for estimating foliar nitrogen in dry miombo woodlands. The contrast texture measure, calculated at increasing window size on Sentinel-2 imagery, was related to field measured nitrogen via random forest regression models. Our results show that the optimum size for estimating nitrogen is 50m. This result is significant in understanding the scale at which dynamics in foliar nitrogen concentration can be remotely measured. [ABSTRACT FROM AUTHOR]

Land-use and land-cover (LULC) mapping in the complex area is a challenging task due to the mixed vegetation patterns, and rough mountains with fast-flowing rivers. In Vietnam, LULC update is not frequently. In this study, we applied a supervised machine learning (Random forest—RF) approach to mapping LULC in Thanh Hoa province, Vietnam from 2011 to 2015 utilizing multitemporal Normalized Difference Vegetation Index (NDVI) data from MODIS, combined with topographic features. Random forest classification (RFC) reached a total prediction accuracy of 91% and Kappa coefficient (K) of 0.89 across eight LULCs. Besides, the results showed that the features extracted from time-series NDVI comprising the mean of yearly NDVI, the sum of NDVI, and the topography were the important variables controlling the LULC classification. For similar studies on the distribution of LULC, the method proposed in this study could be helpful. [ABSTRACT FROM AUTHOR]

The use of remote sensing for examining phenological variation in tropical forests is scarce. The major objectives of the study were to characterize the intra-annual variability of phenological cycle of the Biligiri Ranganathaswamy Temple Tiger Reserve (BRT) and the potentiality of these phenological metrices in defining species assemblages by classifying the forest. Sentinel-2 derived temporal Normalized Difference Vegetation Index (NDVI) data of 2019 was used to extract the vegetation trends and to derive phenological metrics using CropPhenology R package. Seasonal trends revealed that the highest greenness was associated with high NDVI values in September and October. We identified seven vegetation classes in the region and used Random Forest classifier to prepare a community level classification map with an overall classification accuracy of 68.9%. Our results revealed that incorporating the field sampling data and NDVI data can be effectively used for identifying, mapping and monitoring phenology of the BRT landscape.. [ABSTRACT FROM AUTHOR]

This study compares the capability of Landsat-8, Sentinel-2, and ASTER multispectral data in mapping lithological units in the Bukadaban Peak, China, by evaluating the performance of the Random Forest (RF) classifier. Moreover, the study assesses the importance of remote sensing original bands and the bands derived from enhancement techniques such as Principal Component Analysis (PCA) and Minimum Noise Fraction (MNF) to the classification process. Results revealed that RF selected PC8, PC9, PC12, and MNF1 as the most important features in the Sentinel-2 dataset. Several MNF bands of ASTER were more important than the original and PC bands. The original bands were the strongest predictors in Landsat-8 dataset, while PC2, PC5, and MNF5 were relatively significant. Sentinal-2 and ASTER datasets achieved very similar classification accuracy but outperformed Landsat-8 dataset. ASTER dataset yielded the highest overall accuracy 81.8%, which is 0.18% higher than Sentinel-2 and 3.86% higher than Landsat-8. [ABSTRACT FROM AUTHOR]

This study explored the use of multi-source remotely sensed data in monitoring the spatial distribution of pools and pool dynamics in two distinct semi-arid sites in South Africa. The factors that control the pool dynamics were also examined. Three water extraction indices were used, these included Normalised Difference Water Index (NDWI), Modified NDWI and Normalised Difference Vegetation Index. In addition, random forest classifier and Sentinel-1 SAR data were used in mapping pools and pools dynamics for both sites. Overall, the remotely-sensed methods detected and mapped pools with acceptable accuracy, except for small pools (<400 m²). The results suggest that flow occurrences and rainfall are key in controlling temporal changes in pools sizes, and there was no interaction between pools and groundwater. The study showed that remote sensing methods are essential for filling ground monitoring gaps in non-perennial rivers and determining hydrological processes and water availability from pools in semi-arid environments. [ABSTRACT FROM AUTHOR]

This research aims to present a composite approach to characterizing the intra-annual and interannual variability in inlet throat width and understanding its mechanism (how, when, and why it varies). The techniques used include remote sensing imagery analysis, spectral and cross-spectral analyses, correlation analyses, and random forest variable importance. The Da Dien River mouth (DDRM), which is located in southern Central Vietnam and experiences a strong annual signal of climate regimes, was selected as a case study to demonstrate the applicability of the approach. The results show that the narrowing/widening of the DDRM throat width is highly dynamic and variable under the significant dominant influence of wave height, tide and river flow, which seasonally and interannually vary according to the monsoon regime, El Niño/Southern Oscillation and sunspot number variations (better correlation with ENSO events). The overall throat width decreases during El Niño/the positive QBO phase and increases during La Niña periods/the negative QBO phase. The difference in river flow magnitudes is the main cause for the constriction/expansion of the DDRM throat width. The successful application of the study approach to the DDRM case study demonstrates its usefulness and ability to be applied to other case studies in tropical monsoon regions. [ABSTRACT FROM AUTHOR]

Yellowwood or Podocarpus (spp.) holds the esteemed biodiversity status, as key forest species in the mist-belt Afromontane forests of southern Africa. The podocarps are listed as endangered species owing to extensive logging. The forest species support large communities of plants and birds, attributing to the maintenance of biodiversity. Therefore, there is a need to understand the condition of such keystone species if effective and comprehensive biodiversity conservation measures are to be drawn for these dwindling forests. Leaf area index is a crucial eco-physiological parameter applied in the evaluation of the growth and productivity of forest trees, hence it is a suitable proxy for understanding the condition of Yellowwood trees. This study, therefore, sought to estimate the leaf area index of the Yellowwood spp. using Sentinel 2 Multispectral instrument (S2 MSI) data in concert with the Random Forest regression ensemble. Specifically, individual wavebands and vegetation indices were used in developing leaf area index prediction models based on two approaches. The multistage approach, categorised the predictors according to the generalised order of progression, from standard spectral bands to vegetation indices. The second approach involved using a pooled set of predictors, with the backward elimination of poorly performing wavebands and vegetation indices. Results showed that the backward elimination method produced a better model (R2 = 0.59; RMSE = 0.48) when compared to the multistage approach (R2 = 0.50; RMSE = 0.48). The most influential predictor variables in both models were Band 5 and NDVI Red Edge 2. Results of this study underscore the prospects of Sentinel 2 MSI data in characterising the productivity of critical forest species such as the Yellowwoods of the Afromontane forest in southern Africa. The findings of this study are a fundamental step towards understanding forest health and productivity, required in deriving comprehensive monitoring and management strategies in biodiversity conservation. [ABSTRACT FROM AUTHOR]

Mapping the spatial distribution of soil organic carbon (SOC) in lands covered by tropical forests is important to understand the relationship and dynamics of SOC in this type of ecosystem. In this study, the Random Forest (RF) algorithm was used to map SOC stocks of topsoil (0–15 cm) in forest lands of the Dominican Republic. The methodology was developed using geospatial datasets available in the Google Earth Engine (GEE) platform combined with a set of 268 soil samples. Twenty environmental covariates were analyzed, including climate, topography, and vegetation. The results indicate that Model A (combining all 20 covariates) was only marginally better than Model B (combining topographic and climatic covariates), and Model C (only combining multispectral remote sensing data derived from Landsat 8 OLI images). Model A and Model B yielded SOC mean values of 110.35 and 110.87 Mg C ha−1, respectively. Model A reported the lowest prediction error and uncertainty with an R2 of 0.83, an RMSE of 35.02 Mg C ha−1. There was a strong dependence of SOC stocks on multispectral remote sensing data. Therefore, multispectral remote sensing proved accurate to map SOC stocks in forest ecosystems in the region. [ABSTRACT FROM AUTHOR]

This study performed flood risk assessment in urbanized areas using geospatial and remotely sensed data for 1990–2005–2020 periods using the linear unmixing model (LUM), random forests (RF), and support vector machines (SVM). The urban mapping results verified with reference data indicated close agreement, with the overall accuracies and Kappa coefficients higher than 88.9% and 0.78, respectively. A remarkable increase of 14.9% in urban area was observed for the period 2005–2020, compared to 7.2% during the period 1990–2005. The results of flood risk modeling revealed that RF produced slightly more accurate results than SVM. The flood risk areas aggregated with urban maps showed that the larger urban flood risk area was especially observed for the period 2005–2020. The urban areas of high/very high and medium flood risks calculated for 2020 were 19.7% and 20%, respectively. Such flood risk areas were also overlaid with the population density for urban planning and management. [ABSTRACT FROM AUTHOR]

This study aims to predict channel unit types (CUTs) by combining remotely sensed data with morphological variables using machine learning algorithms (random forest, support vector machines, multiple adaptive regression splines, extreme gradient boosting and adaptive boosting) within the Upper Ogun River Basin, Southwestern Nigeria. In achieving the aim of this study, we identified the most important variable(s) in CUT discrimination using the random forest – recursive feature elimination (RF-RFE). A total of 249 cross-sections across 83 reaches were sampled during the fieldwork. Landsat 8 and Sentinel-1 bands were retrieved for days the fieldwork was carried and mosaiced using the Google Earth Engine platform. The RF-RFE identified five top variables (accuracy: 0.79 ± 0.14; kappa: 0.39) discriminating the CUT as dimensionless stream power, slope, width, wetted perimeter and Band 4. In essence, there is much hope in the use of remote sensing in CUT mapping at the reach scale. [ABSTRACT FROM AUTHOR]

The study involves an object-based segmentation method to extract feature changes in tropical rainforest cover using Landsat image and airborne LiDAR (ALS). Disturbance event that are represents the changes are examined by the classification of multisensor data; that is a highly accurate ALS with different resolutions of multispectral Landsat image. Disturbance Index (DI) derived from Tasseled Cap Transformation, Normalized Difference Vegetation Index (NDVI), and the ALS height are the variables for object-based segmentation process. The classification is categorized into two classes; disturbed and non-disturbed forest cover using Nearest Neighbor (NN), Random Forest (RF) and Support Vector Machine (SVM). The overall accuracy ranging from 88% to 96% and kappa ranging from 0.79 to 0.91. Mcnemar's test p-value (<0.05) is applied to check the classification for each method used which is RF 0.03 and SVM 0.01. The accuracy increases when the integration of ALS in Landsat image (SpectralLandsat; and SpectralLandsat + HeightALS). [ABSTRACT FROM AUTHOR]

This paper aims to offer an improved version of the new composite drought monitoring index (CDMI) and to test its applicability in the context of Tensift watershed in Morocco. A synergistic approach incorporating the remote sensing techniques, hydrometeorological data, simulated data and agricultural statistics was used for this purpose. After assessing the performance of CDMI, estimated Soil Moisture Anomaly Indicator (ISMA) was processed, validated and incorporated to the composite model. Random Forest algorithm was used to determine the weight of composite model components. Apart from comparative mapping, Pearson's correlation statistical analysis, linear regression and dependency tests were used to assess the performance of the improved composite model (CDMIa_RF). The result show that CDMIa_RF is better correlated with several indices such as: the Standardized Precipitation Index (SPI), (R2=0.74); Hydrological Drought Index (R2=0.70); grain productivity (R2=0.70), CDMI (R2=0.95), Vegetation Health Index (VHI), (R2=0.87), and Normalized Vegetation Supply Water Index (NVSWI), (R2= 0.85). [ABSTRACT FROM AUTHOR]

One of the main applications of machine learning (ML) in remote sensing (RS) is the pixel-level classification of satellite images into land cover types. Although classes with different spectral signatures can be easily separated, e.g. aquatic and terrestrial land cover types, others have similar spectral signatures and are hard to separate using only the information within a single pixel. This work focused on the separation of two cover types with similar spectral signatures, cocoa agroforest and forest, over an area in Pará, Brazil. For this, we study the training and application of several ML algorithms on datasets obtained from a single composite image, a time-series (TS) composite obtained from the same location and by preprocessing the TS composite using simple TS preprocessing techniques. As expected, when ML algorithms are applied to a dataset obtained from a composite image, the median producer's accuracy (PA) and user's accuracy (UA) in those two classes are significantly lower than the median overall accuracy (OA) for all classes. The second dataset allows the ML models to learn the evolution of the spectral signatures over 5 months. Compared to the first dataset, the results indicate that ML models generalize better using TS data, even if the series are short and without any preprocessing. This generalization is further improved in the last dataset. The ML models are subsequently applied to an area with different geographical bounds. These last results indicate that, out of seven classifiers, the popular random forest (RF) algorithm ranked fourth, while XGBoost (×GB) obtained the best results. The best OA, as well as the best PA/UA balance, were obtained by performing feature construction using the M3GP algorithm and then applying XGB to the new extended dataset. [ABSTRACT FROM AUTHOR]

Soil organic carbon (SOC) is one of the key soil components for cultivated soils. SOC is regularly monitored and mapped to improve the quality, health, and productivity of the soil. However, traditional SOC-level monitoring is expensive for land managers and farmers. Estimating SOC using satellite imagery provides an easy, efficient, and cost-effective way to monitor surface SOC levels. The objective of this study was to estimate the surface SOC distribution in selected soils of Major Land Resource Areas (MLRA), 102A (Rolling Till Plain, Brookings County, SD), and 103 (Central Iowa and Minnesota Till Prairies, Lac qui Parle County, MN), using satellite imagery with different resolutions (Landsat 8 and PlanetScope). The dominant soils in the study area are Haplustolls, Calciustolls, and Endoaquolls, which are formed in silty sediments, local silty alluvium, and till. Landsat 8 and PlanetScope spectral bands were used to develop SOC prediction models. Parametric and data-driven methods were employed to predict the SOC. Multiple linear regression and Linear Spatial Mixed Model (LSMM) were used on the Landsat 8 and PlanetScope data. In addition to the parametric models, Regression Trees and Random Forest were also employed on both satellite data. The results showed that reduced LSMM provided the lowest RMSE, which are 0.401 and 0.367 for Landsat 8 and PlanetScope, respectively. Furthermore, the random forest has the highest RPD and RPIQ for Landsat 8 (RPD of 2.67 and RPIQ of 2.49) and PlanetScope (RPD of 2.85 and RPIQ of 3.7). In all cases, models obtained from PlanetScope are better than those obtained from Landsat 8. [ABSTRACT FROM AUTHOR]

Essential forest ecosystem services can be assessed by better understanding the diversity of vegetation, specifically those of Mediterranean region. A species level classification of maquis would be useful in understanding vegetation structure and dynamics, which would be an indicator of degradation or succession in the region. Although remote sensing was regularly used for classification in the region, maquis are simply represented as one to three categories based on density or height. To fill this gap, we test the capability of Sentinel-2 imagery, together with selected ancillary variables, for an accurate mapping of the dominant maquis formations. We applied Recursive Feature Selection procedure and used a Random Forest classifier. The algorithm is tested using ground truth collected from site and reached 78% and 93% overall accuracy at species level and physiognomic level, respectively. Our results suggest species level characterization of dominant maquis is possible with Sentinel-2 spatial resolution. [ABSTRACT FROM AUTHOR]

Surface longwave net radiation (SLNR) is the key component of the surface radiation budget. SLNR is estimated by using the conventional method, in which surface longwave downward radiation (SLDR) and surface longwave upward radiation (SLUR) are estimated separately, and then SLNR is calculated by subtracting SLUR from SLDR. However, uncertainties in SLDR and SLUR may accumulate and propagate into the calculated SLNR, affecting the SLNR estimate accuracy. This paper proposes a direct algorithm that links clear-sky SLNR with the top-of-atmosphere (TOA) radiances in MODIS channels 29, 31 and 32 and column water vapour (CWV). The multivariate regression (MVR) and extreme gradient boosting (×GBoost) were employed to establish the relationships sequentially with collocated ground measurements and satellite data for high-latitude, mid-latitude, and low-latitude areas. According to the training and validation results, the GBoost model performs slightly better than the MVR model, which indicates that weak nonlinearity exists between clear-sky SLNR and its predictors. The absolute biases of the XGBoost models are approximately 1.0 Wm−2, and the RMSEs of the XGBoost model are 17.77, 27.33, and 19.60 Wm−2 in high-latitude, mid-latitude, and low-latitude areas. These results indicate that nonlinear relationships exist between clear-sky SLNR and predictors, but this nonlinearity is not strong. The superiority of the direct algorithm over the conventional method was also demonstrated. In the future, we will collect more data to improve the performance of the proposed direct algorithm especially in high-latitude and mid-latitude areas. [ABSTRACT FROM AUTHOR]

The retrieval of forest variables from optical remote sensing data using physically-based models is an ill-posed problem and does not make full use of the high spatial resolution imagery that is becoming available globally. A possible solution to this is to use prior information about the retrieved variables, which constrains the possible solutions and reduces uncertainty in forest variable estimation. Therefore, we tried to quantify physically-based parameters that could be retrieved using the second-order statistics of measured and simulated very-high-resolution (pixel size less than 1 m) images of Finnish boreal forests. These forests have a well-defined structure and are usually not closed, i.e. the reflected signal has a considerable contribution from a green forest floor. We retrieved the second-order statistics using variograms and Fourier amplitude spectra. We found, in line with previous studies, that the range of variograms correlates well ( r = 0.83) with the mean crown diameter for spatially homogeneous forest patches, and it can be used to estimate crown diameters with reasonable accuracy (RMSE = 0.42 m). We present a novel approach, which uses the Fourier amplitude spectrum to study the spatial structure of a forest. The approach provided encouraging results with the measured data: despite the lower accuracy (RMSE = 0.67 m) compared with variograms, we found that it could also be used to estimate mean crown diameters for heterogeneous forest areas. The Fourier amplitude spectrum approach did not work with the simulated images. Our results highlight the possibility to obtain further information from very-high-resolution images of forests to solve the ill-posed problem of forest variable estimation from optical remote sensing data using physically-based models. [ABSTRACT FROM AUTHOR]

Snow and cloud discrimination is a main factor contributing to errors in satellite-based snow cover. To address the error, satellite-based snow cover performs snow reclassification tests on the cloud pixels of the cloud mask, but the error still remains. Machine Learning (ML) has recently been applied to remote sensing to calculate satellite-based meteorological data, and its utility has been demonstrated. In this study, snow and cloud discrimination errors were analyzed for GK-2A/AMI snow cover, and ML models (Random Forest and Deep Neural Network) were applied to accurately distinguish snow and clouds. The ML-based snow reclassified was integrated with the GK-2A/AMI snow cover through post-processing. We used the S-NPP/VIIRS snow cover and ASOS in situ snow observation data, which are satellite-based snow cover and ground truth data, as validation data to evaluate whether the snow/cloud discrimination is improved. The ML-based integrated snow cover detected 33–53% more snow compared to the GK-2A/AMI snow cover. In terms of performance, the F1-score and overall accuracy of the GK-2A/AMI snow cover was 73.06% and 89.99%, respectively, and those of the integrated snow cover were 76.78–78.28% and 90.93–91.26%, respectively. [ABSTRACT FROM AUTHOR]

Accurate spatial modelling of forest characteristics is one of the most important challenges in remote sensing applications. In this study, we compared the ability of Multiple Linear Regression (MLR), Geographically weighted regression (GWR), and Random Forest (RF) to estimate different forest attributes based on field sample data and Landsat 8 image. CA was modelled with the highest accuracy compared to other variables using GWR. GWR outperformed other methods. The highest and the lowest values of RMSE were for BA using RF (31.0%) and CA using GWR (12.0%), respectively. [ABSTRACT FROM AUTHOR]

An accurate estimation of forest aboveground biomass (AGB) is important for carbon accounting. In this study, six methods, including partial least squares regression, regression kriging, k-nearest neighbour, support vector machines, random forest and high accuracy surface modelling (HASM), were used to simulate forest AGB. Forest AGB was mapped by combining Geoscience Laser Altimeter System data, optical imagery and field inventory data. The Normalized Difference Vegetation Index (NDVI) and Wide Dynamic Range Vegetation Index (WDRVI0.2) of September and October, which had a stronger correlation with forest AGB than that of the peak growing season, were selected as predictor variables, along with tree cover percentage and three GLAS-derived parameters. The results of the different methods were evaluated. The HASM model had the best modelling accuracy (small MAE, RMSE, NRMSE, RMSV and NMSE and large R2). A forest AGB map of the study area was generated using the optimal model. [ABSTRACT FROM AUTHOR]

Algal blooms are a frequent subject in scientific discussions and are the focus of many recent studies, mainly due to their adverse effect on society. Given the lack of ground truth data and the need to develop tools for their detection and monitoring, this research proposes a novel method to automate detection. Concepts derived from multi-temporal image series processing, spectral indices and classification with One-class Support Vector Machine (OC-SVM) are used in this proposal. Imagery from multi-spectral sensors on Landsat-8 and MODIS were acquired through the Google Earth Engine API (GEE API). In order to evaluate our method, two bloom detection case studies (Lake Erie (USA) and Lake Taihu (China)) were performed. Comparisons were made with methods based on spectral index thresholds. Also, to demonstrate the performance of the OC-SVM classifier compared to other machine learning methods, the proposal was adapted to be used with a Random Forest (RF) classifier, having its results added to the analysis. In situ measurements show that the proposed method delivers highly accurate results compared to spectral index thresholding approaches. However, a drawback of the proposal refers to its higher computational cost. The application of the new method to a real-world bloom case is demonstrated. [ABSTRACT FROM AUTHOR]

The occurrence of drought is related to complicated interactions between many factors, such as precipitation, temperature, evapotranspiration and vegetation. In this study, the relationships between drought and precipitation, temperature, vegetation and evapotranspiration were investigated with a random forest (RF), and a new combined drought monitoring index (CDMI) was constructed. The effectiveness of the CDMI in monitoring drought in Shaanxi Province was verified by the in situ 1 ∼ 12-month standardized precipitation index (SPI); relative soil moisture (RSM) and four other commonly used remote sensing drought monitoring indices. The results show that CDMI is more correlated with the SPI and RSM than the four indices. Moreover, the spatial distributions of drought for the CDMI and RSM are similar. Therefore, the CDMI can be used to monitor droughts in Shaanxi Province, and machine learning can explore the relationships between various factors and establish a drought index without knowledge of the causal mechanisms of these factors. [ABSTRACT FROM AUTHOR]

Herein, a random-forest-based Kriging downscaling method (RFRKriging) was tested to increase the spatial resolution of Landsat 8 thermal-infrared remote sensing (TIRS) brightness temperature (Tb) over the central areas of Guangzhou, China. The 240-m Landsat 8 Tb was upscaled from the resampled 30-m Landsat 8 Tb by using the spatial averaging method. Tb was downscaled based on its relationship to spectral reflectance in visible/near-infrared and shortwave infrared bands, spectral indices, including normalized difference vegetation index (NDVI), normalized difference building index (NDBI), and modified normalized difference water index (MNDWI), digital elevation model (DEM), longitude, latitude, impervious surface, vegetation, and soil fractions. The linear regression Kriging (LRKriging) and NDVI-based thermal sharpening algorithm (TsHARP) regression Kriging (TsHARPKriging) were also implemented. Relative to the reference data from the resampled Landsat 8 Tb, the RFRKriging produced satisfactory downscaling results with respect to the maximum coefficient of determination (R2), the minimum root-mean-square error (RMSE), and the minimum ratio between RMSE and the correspondent Landsat 8 Tb standard deviation (RSD). RFRKriging captured Tb differences over roads, forests, water bodies, and buildings and enhanced the spatial details of downscaled Tb in all urban areas. Furthermore, integrating the multi-type predictor variables from 10-m Sentinel-2A and 30-m Landsat 8 image sets, RFRKriging was further applied to downscale 30-m Landsat 8 Tb to 10 m. Then, it was upscaled to 30 m and assessed with the original 30-m Landsat 8 Tb. RFRKriging was an effective and practical method for increasing the spatial resolution, with a low RSD of 0.254, a low RMSE of 0.525 K and a high R2 of 0.935. The RSD of less than 0.5 indicates that RFRKriging could achieve an acceptable downscaling accuracy. Furthermore, RFRKriging enhances the spatial details of a 10-m Tb in complex urban environments while maintaining the intrinsic information and spatial patterns of a downscaled Tb. Due to the unavailability of the 30-m and 10-m Tb truth, this study may only provide a quantitative assessment from some theoretical experiments. Also, a comparison of the RFRKriging downscaled Tb with the resampled Landsat 8 Tb was performed. The results suggest that the proposed RFRKriging downscaling method shows better downscaling performance with more spatial details than the cubic convolution method applied by the National Aeronautics and Space Administration (NASA) Centre. [ABSTRACT FROM AUTHOR]

Land use–land cover (LULC) change and the associated risk of soil erosion have become a global environmental concern. We herein presented a geospatial analysis to detect LULC changes (1984–2010) in a Canadian watershed by using object-based classification of Landsat satellite images. We found that the watershed experienced a substantial increase in forest clear cutting and built-up areas. The detected LULC changes were implemented into the Revised Universal Soil Loss Equation (RUSLE) to examine the soil erosion potential. We divided the soil erosion risk into five classes ranging from very low (<6 ton ha−1 year−1) to severe (33 ton ha−1 year−1) levels. The random forest algorithm was then implemented and detected that the topography and LULC conditions of 1999 and 2010 had the most influence on the erosion in 2010. The findings of this study will support efficient LULC management to reduce soil erosion and the consequent degradation of water quality. [ABSTRACT FROM AUTHOR]

Semantic segmentation of remote sensing images is an important but unsolved problem in the remote sensing society. Advanced image semantic segmentation models, such as DeepLabv3+, have achieved astonishing performance for semantically labeling very high resolution (VHR) remote sensing images. However, it is difficult for these models to capture the precise outlines of ground objects and explore the context information that revealing relationships among image objects for optimizing segmentation results. Consequently, this study proposes a semantic segmentation method for VHR images by incorporating deep learning semantic segmentation model (DeepLabv3+) and object-based image analysis (OBIA), wherein DSM is employed to provide geometric information to enhance the interpretation of VHR images. The proposed method first obtains two initial probabilistic labeling predictions using a DeepLabv3+ network on spectral image and a random forest (RF) classifier on hand-crafted features, respectively. These two predictions are then integrated by Dempster-Shafer (D-S) evidence theory to be fed into an object-constrained higher-order conditional random field (CRF) framework to estimate the final semantic labeling results with the consideration of the spatial contextual information. The proposed method is applied to the ISPRS 2D semantic labeling benchmark, and competitive overall accuracies of 90.6% and 85.0% are achieved for Vaihingen and Potsdam datasets, respectively. [ABSTRACT FROM AUTHOR]

The Brazilian Atlantic Forest, one of the most threatened tropical regions in the world, exhibits high levels of terrestrial aboveground biomass (AGB). We propose a random forest approach to model, map and assess whether public lands provide protection for AGB in the Rio Doce watershed, one of the most important watercourses of the Atlantic Forest biome. We used 188 field plots and individual and hybrid features from remote sensing, environmental and terrain-related data. The hybrid model improved the AGB prediction by reducing the root mean square error to 33.43 Mg/ha and increasing the coefficient of determination (R2) to 0.57. The total estimated AGB was 178,967,656.73 Mg, ranging from 20.40 to 167.72 Mg/ha following the seasonal precipitation pattern and anthropogenic disturbance effects. Only 5.76% of the total AGB was located on public protected lands, totalling 10,305,501 Mg, while most of the remaining AGB were located on private properties. [ABSTRACT FROM AUTHOR]

Machine learning algorithms such as Random Forest (RF) are being increasingly applied on traditionally geographical topics such as population estimation. Even though RF is a well performing and generalizable algorithm, the vast majority of its implementations is still 'aspatial' and may not address spatial heterogenous processes. At the same time, remote sensing (RS) data which are commonly used to model population can be highly spatially heterogeneous. From this scope, we present a novel geographical implementation of RF, named Geographical Random Forest (GRF) as both a predictive and exploratory tool to model population as a function of RS covariates. GRF is a disaggregation of RF into geographical space in the form of local sub-models. From the first empirical results, we conclude that GRF can be more predictive when an appropriate spatial scale is selected to model the data, with reduced residual autocorrelation and lower Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) values. Finally, and of equal importance, GRF can be used as an effective exploratory tool to visualize the relationship between dependent and independent variables, highlighting interesting local variations and allowing for a better understanding of the processes that may be causing the observed spatial heterogeneity. [ABSTRACT FROM AUTHOR]

LIght Detection And Ranging (lidar) data have been widely used in the areas of ecological studies due to lidar's ability to provide information on the vertical structure of vegetation in wildlife habitats. The overall objective of this project was to map the vegetation on No Name Key, Florida where endangered wildlife species reside using publicly available remote sensing data such as lidar data and high resolution aerial images (including National Agricultural Imagery Program (NAIP) images). The methods involved the use of 4 different classification algorithms (Support Vector Machine, Random Forest, Maximum Likelihood, and Mahalanobis Distance), different classification settings (default and custom settings), and normalization (original and normalized input bands) on 2 different input stacked images, NAIP image alone and NAIP combined with lidar data. A majority filter was applied to each classification output before performing the accuracy assessment. The result of performing the image classifications showed the following: across all inputs and classification algorithms, the highest overall accuracy (OA) and kappa coefficient (к) were achieved by the Random Forest classification on the NAIP-lidar stacked image with an applied majority filter and original input bands. The result also showed the airborne data combined with the lidar data resulted in a higher classification accuracy than the airborne data alone; and when normalization was applied to all the input bands or layers, the classification accuracies were not increased in most cases compared to when original bands were used in the classification. In most cases, the application of the majority filter increased the accuracy of the classification results as opposed to when no majority filter was applied. Instead of using default values, when the new parameter values (i.e., custom settings) for the penalty parameter (C) and the gamma (ɤ) were used, the accuracies of the Support Vector Machine (SVM) classified images were slightly increased compared to using the default values for the 2 parameters. With increased availability of public lidar data, combining the aerial image with lidar data would enhance the accuracy of vegetation mapping, which would lead to more effective and accurate wildlife management. [ABSTRACT FROM AUTHOR]

Remote sensing scene classification is gaining much more interest in the recent few years for many strategic fields such as security, land cover and land use monitoring. Several methods have been proposed in the literature and they can be divided into three main classes based on the features used: handcrafted features, features obtained by unsupervised learning and those obtained from deep learning. Handcrafted features are generally time consuming and suboptimal. Unsupervised learning based features which have been proposed later gave better results but their performances are still limited because they mainly rely on shallow networks and are not able to extract powerful features. Deep learning based features are recently investigated and gave interesting results. But, they cannot be usually used because of the scarcity of labelled remote sensing images and are also computationally expensive. Most importantly, whatever kind of feature is used, the neighbourhood information of them is ignored. In this paper, we propose a novel remote sensing scene representation and classification approach called Bag of Visual SubGraphs (BoVSG). First, each image is segmented into superpixels in order to summarize the image content while retaining relevant information. Then, the superpixels from all images are clustered according to their colour and texture features and a random label is assigned to each cluster that probably corresponds to some material or land cover type. Thus superpixels belonging to the same cluster have the same label. Afterwards, each image is modelled with a graph where nodes correspond to labelled superpixels and edges model spatial neighbourhoods. Finally, each image is represented by a histogram of the most frequent subgraphs corresponding to land cover adjacency patterns. This way, local spatial relations between the nodes are also taken into account. Resultant feature vectors are classified using standard classification algorithms. The proposed approach is tested on three popular datasets and its performance outperforms state-of-the-art methods, including deep learning methods. Besides its accuracy, the proposed approach is computationally much less expensive than deep learning methods. [ABSTRACT FROM AUTHOR]

Water hyacinth, Eichhornia crassipes (C. Mart) Solms (Pontederiaceae), is an invasive aquatic macrophyte with major negative economic and ecological impacts in Rwanda and other East African countries since its establishment in the region in the 1960s. Reliable estimates of water hyacinth distribution are required to determine the severity of the problem and identify waterbodies requiring management. Remote sensing techniques, based on the Landsat 8 sensor, offer promising alternatives to accurately detect, map and monitor the extent of the water hyacinth invasion in Rwandan waterbodies. The aim of the current study was to investigate the utility of multispectral remote sensed imagery using Random Forest and Support Vector Machine algorithms to detect and map water hyacinth in Rwandan waterbodies. Random Forest had a high overall accuracy of 85%, compared with Support Vector Machine (65%). These algorithms confirmed different levels of water hyacinth infestations in three main Rwandan rivers. Many of the wetlands along these riparian systems and most of the lakes, particularly those from the Eastern Province of the country were found to be invaded by water hyacinth. These findings would, therefore, assist government partners and policy makers to put in place sustainable methods, such as biological control, along with integrated pest management, to control the of water hyacinth invasion in Rwanda. [ABSTRACT FROM AUTHOR]

Combining optical and polarimetric synthetic aperture radar (PolSAR) earth observations offers a complementary data set with a significant number of spectral, textural, and polarimetric features for crop mapping and monitoring. Moreover, a temporal combination of both sources of information may lead to obtaining more reliable results compared to the use of single-time observations. In this paper, an operational framework based on the stacked generalization of random forest (RF), which efficiently employed bi-temporal observations of optical and radar data, was proposed for crop mapping. In the first step, various spectral, vegetation index, textural, and polarimetric features were extracted from both data sources and placed into several groups. Each group was classified separately using a single RF classifier. Then, several additional classification tasks were accomplished by another RF classifier. The earth observations used in this paper were collected by RapidEye satellites and the Unmanned Aerial Vehicle Synthetic Aperture Radar (UAVSAR) system over an agricultural region near Winnipeg, Manitoba, Canada. The results confirmed that the proposed methodology was able to provide a higher overall accuracy and kappa coefficient than traditional stacking method, and also than all the individual RFs using each group. These accuracy metrics were also better than those of the RFs using the stacked features. Moreover, only the proposed methodology could achieve standard accuracy (F-score ≥85%) for all crop types in the study area. The visual comparison also demonstrated that the crop maps produced by the proposed methodology had more homogeneous, uniform appearances. Moreover, the mixed pixels of crop types, which abundantly existed in the traditional stacking and individual RFs̕ maps, were significantly eliminated. [ABSTRACT FROM AUTHOR]