Search

The Karakoram Highway (KKH) is a pivotal gateway within the framework of the China-Pakistan Economic Corridor. Nevertheless, its distinct and intricate geographical characteristics make it susceptible to recurrent landslides. As an essential tool, landslide susceptibility mapping (LSM) is significant in managing and alleviating landslides near the KKH. Moreover, landslide conditioning factors (LCFs) are crucial determinants influencing the outcomes of LSM. However, existing methods primarily rely on machine learning algorithms, which do not adequately account for the intricate spatial characteristics and patterns between LCFs and landslide occurrences. In response, this study introduces the feature fusion transformer (FFTR) module, constructed based on the foundations of the transformer framework, to fuse the spatial information features of all LCFs. Subsequently, the abstract high-level spatial features obtained are fed into diverse machine learning classifiers, including random forest (RF), extreme gradient boosting (XGBoost), gradient boosting decision trees (GBDT), categorical boosting (CatBoost), and extremely randomized trees (ET), to generate landslide susceptibility maps. Displacement velocity calculated by Persistent Scatterer Interferometric Synthetic Aperture Radar (PSInSAR) is incorporated in the LSM. The results demonstrate that FFTR-RF achieves premium performance in the area under the curve (AUC) (94%), accuracy (87.31%), precision (87.21%), recall (88.02%), and F1-score (87.61%). Incorporating displacement velocity into LSM results predicted by models enhances the comprehensiveness of LSM. These methods will furnish early warning systems for landslide disasters along the KKH, thus aiding recommendations for mitigating landslides' social and economic losses. [ABSTRACT FROM AUTHOR]

Fire was a serious natural disturbance to forest ecosystems. In this study, a national-scale forest fire risk model (RF_NTL) was proposed in mainland China by incorporating a new human activity factor (NTL) from nighttime light data. For objective verification of model's performance, the logistic regression model (LR) and random forest model (RF) were also built in this paper. Results showed that the RF_NTL model fitted with an AUC value up to 0.95, which was superior to the conventional LR model and RF model. The RF_NTL model also had good generalization ability and stability on annual and monthly scales, helping to accurately forecast forest fire risk. Moreover, the spatial distribution of forest fire risk based on RF_NTL model was detailed and reasonable on a national scale. Forest fire high-risk areas in China were mainly concentrated in the northeast and southwest regions. This study could provide references for future relevant research. [ABSTRACT FROM AUTHOR]

This study makes a significant contribution to the field of groundwater potential mapping (GWPM) by exploring the application of ensemble learning models (ELMs), specifically boosting ensemble models (BEMs), which have not been fully utilized in GWPM. By employing six ELMs (random forest, AdaBoost, XGBoost, CatBoost, GBDT and LightGBM), along with Tree-structured Parzen Estimator in Luoning County, China, this study identifies key indicators (topographic position index, distance to rivers and topographic wetness index) and demonstrates the superior model performance of XGBoost compared to other ELMs. Additionally, correlation analysis confirms the accuracy of XGBoost in predicting relationships between important indicators and groundwater potentials. Finally, the findings provide valuable insights for sustainable groundwater management strategies in Luoning County and emphasize the need for further exploration of ELMs, development of comprehensive performance evaluation and indicator systems, reduction of the inconsistencies between indicators and predication results and practical research to support future sustainable groundwater management. [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]

As urbanization accelerates, the degree of human impact on land use is increasing. land use land cover change (LULC) is acknowledged as crucial factor in environmental change. The best way to understand historical land use patterns, changes, drivers, and developments is through a rigorous assessment of LULC changes. In this study, we aim to identify LULC changes from 2015 to 2022, and predict changes for 2030. Sentinel-2 images were employed to analyze LULC change patterns and predict future trends. The Random Forest algorithm was used to classify the various LULC classes with high accuracy and reliability. Multilayer Perceptron and Markov Chain Analysis (MLP-MCA) based Hybrid-Approach was employed to predict the future dynamics of LULC change for 2030. The study revealed that built-up area expanded 90.64 km2 from 2015 to 2022 due to natural resource substitution. Predictions indicate that 58.84% of the study area will be transform into built-up by 2030. [ABSTRACT FROM AUTHOR]

This study, which aims to make predictions using a previously unused deep hybrid Convolutional Neural Network-Support Vector Regression approach for hydropower generation, was carried out using a unique meteorological data set as input data. The unique dataset was collected from Kaman Meteorology Directorate and Hirfanlı HEPP in Turkey, from 2007 to 2021, to estimate the HEPP's Net Head and Hydroelectric Power Generation on a daily basis. The performances of the prediction models were benchmarked in addition to the used CNN-SVR model with Machine Learning (ML) models (Boosting Random Forest Regression (BRFR) and Weighted K-Nearest Neighbor Regression (WKNNR)) and Deep Learning (DL) models (Long-Short Term Memory (LSTM) and Deep Belief Network (DBN)). The comparison results of the used CNN-SVR model with other alternative models showed that CNN-SVR performed effectively with the highest correlation coefficient of 0.971 for NH and 0.968 for PP. [ABSTRACT FROM AUTHOR]

Population growth and environmental shifts have elevated the pressure on land use and cover (LULC), necessitating vital management and adaptive strategies to preserve the balance between ecosystem services and human well-being in watersheds. It's pivotal to understand the implications of human-induced shifts from natural to human-dominated surroundings This study utilized Google Earth Engine (GEE) to analyze 31 years of LULC changes in Letaba watershed. Using GEE's random forest, LULC classes were mapped with 93% to 99% accuracy across four timeframes (1990, 2000, 2010, and 2021). Trends revealed declining water bodies (-4%), bare surfaces (-2%), natural forest (-3%), and grassland (-3%), while shrublands, plantations, and built-up areas increased at annual rates of 41%, 24%, and 47% respectively. This transformation reflects population-driven shifts, necessitating adaptive strategies. Given the importance of plantations for income, embracing climate-smart agriculture could ensure long-term food and environmental security, thus addressing the evolving dynamics in Letaba watershed. [ABSTRACT FROM AUTHOR]

In this paper, we examined the degree to which inherent spatial structure in soil properties influences the outcomes of machine learning (ML) approaches to predicting soil spatial variability. We compared the performances of four ML algorithms (support vector machine, artificial neural network, random forest, and random forest for spatial data) against two non-ML algorithms (ordinary least squares regression and spatial filtering regression). None of the ML algorithms produced residuals that had lower mean values or were less autocorrelated over space compared with the non-ML approaches. We recommend the use of random forest when a soil variable of interest is weakly autocorrelated (Moran's I < 0.1) and spatial filtering regression when it is relatively strongly autocorrelated (Moran's I > 0.4). Overall, this work opens the door to a more consistent selection of model algorithms through the establishment of threshold criteria for spatial autocorrelation of input variables. [ABSTRACT FROM AUTHOR]

Urban land use/land cover (LULC) classification has long been a hotspot for remote sensing applications. With high spatio-temporal resolution and multispectral, the recently launched GF-6 satellite provides ideal open imagery for LULC mapping. In this study, we utilized multitemporal GF-6 images to generate six types of land features, including spectral bands, texture features, built-up, waterbody, vegetation, and red-edge indices. The minimum Redundancy Maximum Relevance (mRMR) algorithm was employed to optimize feature selection. Subsequently, Random Forest (RF) and Extreme Gradient Boosting (XGBT) were assessed using different feature selections. Besides, various feature configurations were designed for LULC classification and comparison. The results indicate that the mRMR-based RF method achieved the highest overall accuracy of 91.37%. The temporal red-edge indices were important features for urban LULC classification and contributed mainly to grassland and cropland. These results supplement existing classification methods and assist in improving LULC mapping in urban areas with complex landscapes. [ABSTRACT FROM AUTHOR]

Vegetation hinders the acquisition of bedrock spectra and makes it difficult to classify bedrock with remote sensing data. Previous studies indicated bedrock can control vegetation growth through soluble nutrients and water-holding capacity. However, the potential of using vegetation spectral features to map bedrock has been rarely explored. This study first derived reflectance and vegetation indices from time series Sentinel-2 products, then did a spatiotemporal analysis of vegetation spectral features on different bedrock, and finally combined vegetation features and random forest classifiers to map bedrock. The results demonstrated that (a) the close relationship between vegetation growth and bedrock can be captured by Sentinel-2 images; (b) both VIs' combination and reflectance derived from the growing season can achieve reasonably classified maps, with classification accuracies of 70.06% and 73.46%, respectively; (c) NDVI was more sensitive to the bedrock than other VIs. Overall, vegetation spectral features showed great potential to map bedrock underneath vegetation. [ABSTRACT FROM AUTHOR]

Maize is a staple food, but productivity has stagnated due to limited access to advanced farming methods and knowledge. To promote sustainable agriculture, understanding the factors affecting maize yield at the farm level is crucial. This study used panel data on maize yield and agronomic practices in Northern Ghana and Malawi from 2014 to 2020. Satellite-based environmental variables were extracted at household locations, and Random Forest modeling was used to identify factors influencing maize yield variability. The models performance was sub-par with low R2 values (∼0.1 and ∼0.24 for Northern Ghana and Malawi). Fertilizer and precipitation were the most important factors explaining maize yield variability. Spatial maps showed that Malawi's maize yield can increase with more fertilizer, but rainfall is essential. In Northern Ghana, relying solely on fertilizer may not be enough to boost maize production. Survey data on maize is limited in making accurate yield predictions. Fertilizer use can increase maize yield in both Northern Ghana and Malawi. Fertilizer use intervention strategies should be region-specific. The efficiency of fertilizer use is dependent on adequate rainfall availability. [ABSTRACT FROM AUTHOR]

Transboundary forests in the Himalayas are one of the world's biodiversity hotspots, but exploring the patterns and influencing factors related to forest disturbance-recovery is still limited. In this study, we used a random forests model, a LandTrendr temporal segmentation algorithm and geographical detector to investigate the spatial and temporal evolution characteristics of forest disturbance and recovery and their influencing factors in the central Himalayas from 1995 to 2018. The results showed that forest disturbance was dominant (∼2.94 × 104 km2) and greater than recovery (∼0.56 × 104 km2). Both disturbance and recovery showed a significant decreasing trend (p < 0.01); disturbance occurred mainly at low elevations and the Gandaki basin, while recovery was in eastern Nepal. Disturbance rates were highest in Nepal (1.14%) and recovery rates in China (0.29%). The main influencing factors on forest dynamics were elevation, temperature and population. The interaction of all factors was synergistically enhanced. [ABSTRACT FROM AUTHOR]

Aiming to provide a scientific basis for the prevention and control of soil erosion in the Huaihe region, this study uses the InVEST-SDR model to estimate the temporal and spatial changes of soil erosion and soil conservation in the Huaihe region in 2010, 2015 and 2020, and the driving factors are evaluated and quantified using Random Forest and Geodetector, respectively. The major findings are as follows: (1) From 2010 to 2020, soil loss and soil retention in the Huaihe region gradually intensified, while the spatial distribution trend was consistent from year to year. (2) The results from Random Forest and Geodetector show that changes in soil loss and soil retention are mainly influenced by slope and rainfall. (3) The steepness and length of slopes are the most influencing factors for soil erosion. Soil loss and soil retention vary widely between different land uses. Forests play an important role in soil conservation. [ABSTRACT FROM AUTHOR]

It is a fundamental task to monitor the topography and understand the changes of intertidal zone for rational utilization and sustainable development. A new method is proposed for identifying the terrain of the intertidal zone, using ICESat-2 data to replace a large amount of on-site observation data, thereby reducing costs and improving efficiency. Based on pre-experiments and correlation analysis, time phase index, water index, water transparency index and suspended sediment concentration index are added as features for the random forest (RF). Compared with using only the original band as the model input, the RMSE is reduced by 0.08 m. The results show that the inverted terrain has an RMSE of 0.45 m compared with handheld RTK data, and the RMSE at the mudflat from UAV data is 0.20 m. Based on the analysis of terrain changes over the four-year period, the trend towards sedimentation closer to land becomes more pronounced. [ABSTRACT FROM AUTHOR]

We used the Cellular Automata Markov (CA-Markov) integrated technique to study land use and land cover (LULC) changes in the Cholistan and Thal deserts in Punjab, Pakistan. We plotted the distribution of the LULC throughout the desert terrain for the years 1990, 2006 and 2022. The Random Forest methodology was utilized to classify the data obtained from Landsat 5 (TM), Landsat 7 (ETM+) and Landsat 8 (OLI/TIRS), as well as ancillary data. The LULC maps generated using this method have an overall accuracy of more than 87%. CA-Markov was utilized to forecast changes in land usage in 2022, and changes were projected for 2038 by extending the patterns seen in 2022. A CA-Markov-Chain was developed for simulating long-term landscape changes at 16-year time steps from 2022 to 2038. Analysis of urban sprawl was carried out by using the Random Forest (RF). Through the CA-Markov Chain analysis, we can expect that high density and low-density residential areas will grow from 8.12 to 12.26 km2 and from 18.10 to 28.45 km2 in 2022 and 2038, as inferred from the changes occurred from 1990 to 2022. The LULC projected for 2038 showed that there would be increased urbanization of the terrain, with probable development in the croplands westward and northward, as well as growth in residential centers. The findings can potentially assist management operations geared towards the conservation of wildlife and the eco-system in the region. This study can also be a reference for other studies that try to project changes in arid are as undergoing land-use changes comparable to those in this study. [ABSTRACT FROM AUTHOR]

Vietnam is the world's second-largest coffee exporter. Information on coffee-growing areas is thus important for production estimation. This research developed an approach for coffee mapping and change detection using Landsat and DEM data in Central Highlands, Vietnam. The data were processed for 1995, 2005, and 2020 using random forests (RF). The mapping results, verified with reference data, showed overall accuracy and Kappa coefficient higher than 86.9% and 0.74, respectively. These findings were reaffirmed by a close relationship between the satellite-based coffee area and official statistics, with the root mean squared percentage error (RMSPE) and mean absolute percentage error (MAPE) greater than 9.9% and 7.6%, respectively. From 1995 to 2020, the newly planted coffee area increased by 135,520 ha, due to the conversion of forests to coffee plantations. Such distributions of coffee areas and decadal changes in farming activities are critically useful for policymakers to formulate successful crop planning strategies. [ABSTRACT FROM AUTHOR]

Accurate land cover mapping is challenging in Southeast Asia where cloud coverage is prevalent and landscape is heterogenous. Object-based mapping, multi-temporal images and combined use of optical and microwave data, provide abundant features in spectral, spatial, temporal, geometric and polarimetric dimensions. And random forest is usually employed due to robustness and efficiency in handling high-dimensional and noisy data. This study assesses whether feature selection and ensemble analysis, which are rarely adopted, yield improved result. Recursive feature elimination decreases original 568 features into a subset of 53 features, achieving the optimal combination of features. Ensemble analysis of random forest, support vector machine, and K-nearest neighbors leads to an overall accuracy of 0.816. Comparison experiments demonstrated the merits of the multi-temporal, multi-source approach, feature elimination and ensemble analysis. [ABSTRACT FROM AUTHOR]

In 2014, the State of Telangana in southern India began repairing and restoring more than 46,000 irrigation water tanks (artificial reservoirs) under the Mission Kakatiya project with an investment in excess of USD 2 billion. In this study, we attempted to map the temporal changes that have occurred in cropland areas and water bodies as a result of the project, using remote sensing imagery and applying land use/land cover (LULC) mapping algorithms. We used 16-day time series data from Landsat 8 to study the spatial distribution of changes in water bodies and cropland areas over the 2013–18 period. Ground survey information was used to assess the pixel-based accuracy of the Landsat-derived data. The areas served by these tanks were identified on the basis of training data and Random Forest algorithms using Google Earth Engine. Our spatial analysis revealed a substantial increase in cropped area under irrigation and expansion of water bodies over the study period. We observed a 20% increase in total tank area in 2017–18 and total cropland and irrigated area expansion of the order of 0.6 M ha and 0.2 M ha, respectively. A comparison of ground survey data and four LULC classes derived from Landsat temporal imagery showed an overall accuracy of 87%, significantly correlated with national agriculture statistics. Periodic monitoring based on remote sensing has proved to be an effective method of capturing LULC changes resulting from the Mission Kakatiya interventions. Higher-resolution satellite data can further improve the accuracy of estimates. [ABSTRACT FROM AUTHOR]

Seagrass ecosystems are crucial to the carbon cycle, biodiversity, fisheries, and erosion prevention. However, there are gaps in mapping seagrass in tropical coastal waters due to turbidity and constantly changing tidal dynamics. To tackle such issues, tidal heights and reflectance of 33 Sentinel-2 images were used to calculate a multitemporal composite of Sentinel-2 images, which was classified using the Random Forest classifier. UAV images classified with Object-based image analysis provided ground truth for training and validation. The effectiveness of water column correction and using the multitemporal composite was evaluated by comparing overall classification accuracy. As a result, applying water column correction improved classification accuracy from 80.4% to 80.6%, while using the multi-temporal composite improved accuracy to 88.6%, among the highest accuracy achieved for seagrass classification in turbid waters. The combined protocol could lead to advances in quantifying seagrass distribution in the tropical coastal waters and their carbon sequestration capacity, resolving significant uncertainties in blue carbon estimation. [ABSTRACT FROM AUTHOR]

This study proposed a comprehensive approach that utilized PlanetScope imagery for classifying tropical-marine benthic habitats after retrieving bathymetry from ICESat-2 data and water-column correction for areas around Lyson Islands, Vietnam. Exact bathymetry derivation and water column correction were applied to the PlanetScope imagery, making it an effective method for mapping marine benthic habitats. Water column correction was achieved by applying Depth Invariant Index (DII) and Bottom Reflectance Index (BRI). Moreover, two conventional machine learning algorithms, including Random Forest and Support Vector Machine, and a current deep Convolutional Neural Network (CNN) was employed to classify the benthic features. The overall accuracy of these classifiers are 80.74%, 84.19%, and 89.80% with the BRI, 80.17%, 82.75%, and 87.85% with the DII compared to 37.64%, 42.5%, and 47.2% of without corrected water columns respectively. The CNN model demonstrated that the approach significantly maximizes the improvement in benthic classification results in coastal region. [ABSTRACT FROM AUTHOR]

Estimation of carbon stock in seagrass meadows is in challenges of paucity of assessment and low accuracy of the estimates. In this study, we used a fusion of the synthetic aperture radar (SAR) Sentinel-1 (S-1), the multi-spectral Sentinel-2 (S-2), and coupled this with advanced machine learning (ML) models and meta-heuristic optimization to improve the estimation of total organic carbon (TOC) stock in the Zostera muelleri meadows in Tauranga Harbour, New Zealand. Five scenarios containing combinations of data, ML models (Random Forest, Extreme Gradient Boost, Rotation Forest, CatBoost) and optimization were developed and evaluated for TOC retrieval. Results indicate a fusion of S1, S2 images, a novel ML model CatBoost and the grey wolf optimization algorithm (the CB-GWO model) yielded the best prediction of seagrass TOC (R2, RMSE were 0.738 and 10.64 Mg C ha−1). Our results provide novel ideas of deriving a low-cost, scalable and reliable estimates of seagrass TOC globally. [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]

Spatial information on land and soil resources are critical towards addressing land degradation for ensuring sustainable soil and crop management. To address these needs, digital soil mapping techniques have emerged as an efficient and low-cost solution. Although digital soil mapping has typically leveraged geospatial environmental variables (e.g. remote sensing), the application and integration of spectroscopic data with those environmental variables remain limited. Hence, this study combines visible and nearinfrared (Vis-NIR) spectroscopy, remote sensing, and topographic data and applies random forests, hybridized with particle swarm optimization algorithm (RF + PSO), to predict the spatial variability of soil clay content, electrical conductivity (EC), and calcium carbonate equivalent (CCE) for 370km² of agricultural land in western Iran. Using a conditioned Latin hypercube approach, 220 soil samples at the 0–20 cm depth increment were acquired throughout the study area. Three sets of environmental covariates were tested: Scenario A (Vis-NIR spectroscopy data), Scenario B (environmental data), and Scenario C (Vis-NIR spectroscopy þ environmental data). According to the 10-fold crossvalidation procedure with 100 replications, the RF + PSO model showed an acceptable level accuracy for all scenarios, although the accuracy of the RF + PSO model using the Scenario C data was higher than all other scenarios: the Lin’s Concordance Correlation Coefficient values were 0.77, 0.83, and 0.74 for the clay contents, EC, and CCE, respectively. The results demonstrated that the combination of Vis-NIR spectroscopic data and commonly available environmental covariates provided the best input data for the hybridized model and enhanced its performance. [ABSTRACT FROM AUTHOR]

Flash floods are one of the most serious mountain disasters in Linzhi, China, pose a grave threat to the lives and property of the residents. However, the current regional vulnerability research cannot meet the needs of refined disaster prevention and mitigation in mountainous areas. Therefore, to address this knowledge gap, this study presented a vulnerability assessment framework base on spatialization technique along with the triangular fuzzy number-based analytic hierarchy process (TFN-AHP) and random forest (RF) model. To achieve this goal, an assessment system containing 12 indicators was constructed from the three perspectives of exposure, susceptibility and coping capacity. Firstly, factor spatialization is introduced in data preprocessing. Then TFN-AHP and the RF model were used to calculate the exposure, susceptibility, and coping capacity. Finally, the spatial distribution of the vulnerability throughout Linzhi was obtained. According to the results, the exposure, susceptibility and coping capacity in most areas are extremely low and low, accounting for 74.1%, 99% and 99%, respectively. The vulnerability is similar to the exposure that most of the regions have extremely low vulnerability and low vulnerability, accounting for 83.5%. The moderate vulnerability regions account for 8.5%, and the high vulnerability regions account for only 1%. The assessment results show that highexposure areas mainly exhibit a linear distribution, and mainly include river valleys, cultivated land, and residential areas. Obviously, these areas are mainly distributed in the population and economic agglomeration areas and on low-altitude terrain. The distribution of high and comparatively high vulnerability zones, where economic and human activities are considerably high, are closely to the topography of the catchment. Thus, the results of this study provide scientific and technological evidence for resettlement, population distribution adjustment, and prevention and mitigation of flash floods in Linzhi. [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]

Sample point based spatial model derived from Machine Learning (ML) algorithms often generalizes the spatial pattern of an event. The present study has tried to highlight how far it is acceptable and can it replace with pixel based modeling? The present study has presented a comparative view of pixel and sample point based modeling of gully erosion susceptibility of the upper Mayurakshi basin to assess the predictabilities. Random forest (RF), Support Vector Machine (SVM), and (ADB) have been applied for developing pixel and point based models in Python and WEKA software environments respectively. The models show that 14–25% area located mainly in the upper parts of the study unit is very highly susceptible to gully erosion. Based on the accuracy and performance level using area under curve (AUC) of Receiver operating curve, sensitivity, precision, F1 score, MCC, pixel based ensemble models are superior to point based modeling. The point-based models often have an inferior agreement with training and testing data. So, pixel based models could not be replaced with point based models. RF is found as the best representative model. The study, therefore, recommends using pixel based modeling for this or a similar purpose. Since the models have figured out the gully erosion susceptible areas, it would be a useful tool for related planning processes. [ABSTRACT FROM AUTHOR]

Wildfires are serious threats to Belize’s protected areas and ecosystems. In Belize the spatial variability of wildfire susceptibility and influencing factors at a national scale are poorly understood which hinders wildfire management interventions. Hence, in this research we conducted a joint application and performance comparison of AHP (Analytical Hierarchical Process), RF (Random Forest) and FAHP (Fuzzy Analytical Hierarchical Process). The analysis revealed that RF (AUC = 83.1%) is the model with better predictive accuracy followed by FAHP (AUC = 71.2) and AHP (AUC = 66.8). The RF, AHP and FAHP models classified 22%, 32% and 37% of the country as having high and very high wildfire susceptibility, respectively. These susceptible areas are located mainly in lowland savanna and lowland broad-leaved moist forest; especially, in areas that are unprotected, the outer boundaries of protected areas and small and isolated protected areas. The main factors that are influencing wildfire susceptibility in Belize are distance to agriculture, landcover and temperature. The comparison of these methods provides a better understanding of the implementation and performance of knowledge-based methods (AHP and FAHP) in comparison with a well-established machine learning method (RF) in a country where local data availability, accessibility and reliability are an issue. Our study also provides new wildfire susceptibility information to Belize’s wildfire managers and demonstrates the need to improve wildfire management. [ABSTRACT FROM AUTHOR]

In the present study, three widely used modeling approaches: (1) sediment rating curve (SRC) and optimized OSRC, (2) machine learning models (ML) (random forest (RF) and Dagging-RF (DARF)) and (3) the semi-physically based soil and water assessment tool (SWAT) are applied to predict suspended sediment load (Qs) at the Talar watershed in Iran. Various graphical and quantitative methods were used to evaluate the goodness of fit. Results indicated that the RF model had the best prediction power in the training phase, while the dagging-RF hybrid algorithm outperformed all other models in the validation phase. The OSRC, RF and DA-RF had ‘very good’ performances based on the NSE in the validation phase, SRC showed ‘good’ performance, while the predicted values using SWAT were ‘satisfactory’. Our results suggest that the OSRC and ML models are more suitable for prediction of Qs in study catchments with poor data availability. [ABSTRACT FROM AUTHOR]

The past landslides from landslide inventory are essential for machine learning (ML)-based landslide susceptibility assessment (LSA). They determine not only the positive samples (characterized by the past landslides) but also the negative samples (randomly generated based on past landslides) for training and validating the ML models. However, the number of past landslides is often limited because of the constraints of time, budget, and resources available, etc. In other words, the available data for establishing landslide susceptibility ML models are limited, which indicates that the accuracy and reliability of the corresponding models are insufficient. This article, therefore, proposes using a new landslide susceptibility index-based sampling strategy to enhance the positive and negative samples for model training and validation to reach an improved ML-based LSA. To realize this idea, landslide susceptibility analysis based on initial datasets compiled from landslide inventory by using three ML models, i.e., random forest (RF), gradient boosting decision tree (GBDT) and support vector machine (SVM), are first conducted to obtain the initial landslide susceptibility indices at different space locations. Then, the landslide susceptibility indices are analyzed with the proposed sampling strategy which considers directly the grid units with very high and very low landslide susceptibility indices as potential positive and negative samples, respectively, to enrich the initial dataset; and the number of these positive/negative samples is determined by a Bayesian optimization algorithm. Thereafter, the ML models are updated with the enriched datasets. Finally, to verify the effectiveness of the proposed strategy, the improved models are applied to assess the landslide susceptibility of Taojiang County, China, and the results are compared with those from initial corresponding models without updating. The results show that compared with the initial RF, GBDT and SVM models, the corresponding improved models have a better performance in accuracy, precision, recall rate, and specificity. In particular, the AUC values of the three models are increased by 11.94%, 10.72% and 0.57%, respectively. [ABSTRACT FROM AUTHOR]

Study on pearl millet discrimination in mixed cropping environment was carried out as it forms the major coarse cereal crop in India. The study aims at determining the capabilities of Sentinel1A SAR data and Machine Learning (ML) algorithms for pearl millet discrimination. Six ML algorithms, that is, k-nearest neighbour (k-NN), Decision Tree (DT), support vector machine (SVM), random forest (RF), multi-layer perceptron (MLP) and Naïve Bayes (NB) were evaluated and compared. Meta-classifier using majority voting technique was proposed by ensembling classifiers (RF, SVM and NB) which were diverse and have comparable accuracies. The diversity assessment was conducted using Cochran Q statistics for ensembling purpose. RF classifier (83.76%) using VH polarization produced better result indicating importance of cross-polarization in crop classification. Further, meta-classifier proposed in the study improved the accuracy to 88.15% (approximately by 5%) and class accuracies of pearl millet resulting in improved discrimination of pearl millet in mixed cropping environment. [ABSTRACT FROM AUTHOR]

The leaf area index (LAI) is an important agroecological physiological parameter affecting vegetation growth and is an essential indicator for estimating crop growth. To apply the hybrid machine learning model to the remote sensing inversion of winter wheat LAI at three growth stages based on the wide field of view (WFV) of the GaoFen-6 (GF-6 WFV) images, the Xiangfu District in the east of Kaifeng City, Henan Province, was selected as the testing region. The LAI values, which were simulated using the CERES-wheat model, were an input for the PROSAIL model to simulate spectral reflectance. Different machine learning regression algorithms (MLRA) were trained with simulated spectra reflectance by PROSAIL and subsequently applied to the GF-6 WFV reflectance spectra. The random forest regression (RFR) model achieved reliable LAI estimates at the three growth stages. CERES-wheat and PROSAIL preserved the most informative spectra reflectance for LAI estimation so that each RFR could achieve satisfactory estimation results. The hybrid machine learning model could accurately reverse the growth state of winter wheat in three growth stages. [ABSTRACT FROM AUTHOR]

3D road mapping is essential for intelligent transportation system in smart cities. Road environment receives its data from mobile laser scanning (MLS) systems in the format of LiDAR point clouds, which are distinguished with their accuracy and high density. In this paper, a mobile LiDAR data classification method based on machine learning (ML) is presented. First, data subsampling and slicing are applied, followed by cylindrical neighbourhood selection method to determine the neighbourhood of each point. Second, a new LiDAR-based point feature namely Zmod is introduced, and used along with existing fifteen geometric features as input for a ML algorithm. Finally, Random Forest classifier is applied to a part of (Paris-Lille-3D) MLS point clouds belonging to NPM3D Benchmark. The dataset is about 1.5 km long road in Lille, France with more than 98 million points. The use of Zmod improved the accuracy from 90.26% to 95.23% and achieved sufficient results for classes with low points’ portion in the dataset. In addition, the Zmod is the third important feature in the classification process among the sixteen features with about 14.63%. Moreover, using the first six important features achieved almost the maximum overall accuracy with about 60% reduction in the processing time. [ABSTRACT FROM AUTHOR]

The objective of the present study was to introduce a novel methodological approach for flash flood susceptibility modeling based on a stacking ensemble (SE) model. Two SE models, Random Forest (RF) and Artificial Neural Network (ANN) were developed, whereas LDA, CART, LR, k-NN and SVM were the basic models of the two SE models. The performance of the developed methodology was evaluated at the Island of Rhodes, Greece. The database included 54 flash floods locations and 14 flood-related parameters. The SE-RF model produced slightly higher predictive results, in terms of accuracy (0.844), kappa index (0.687) and the area under the receiver operating characteristic curve (0.870), followed by the SE-ANN with values of 0.812, 0.625 and 0.773, respectively. Overall, the study provides evidence about the higher accuracy SE models can achieve since they are capable of combining in an intelligent way a number of weak predictive models. [ABSTRACT FROM AUTHOR]

The study focuses on the preparation of landslide susceptibility maps in the Kali River valley, Kumaun Himalaya using three machine learning algorithms, namely K-nearest neighbour (KNN), random forest (RF) and extreme gradient boosting (XGB). Fifteen landslide conditioning factors (LCFs) were selected and an inventory of 368 landslides was used for the analysis. Multicollinearity analysis using the variation inflation factor, tolerance and Pearson correlation coefficient (PCC) depicted less to no similarity between all factors. Evaluation of variable importance suggests LCFs such as slope, elevation and distance to thrust contributed significantly and consistently for all three models. Model accuracy was determined and compared using the area under the receiver operating characteristic curve and other statistical signifiers like accuracy, sensitivity, F-measure, accuracy, specificity and recall. The results show that the ensemble algorithms, XGB and RF, yield higher accuracy of approximately 85% compared to the KNN model with 81% accuracy. [ABSTRACT FROM AUTHOR]

Seagrass percent cover is a crucial and influential component of the biophysical characteristics of seagrass beds and is a key parameter for monitoring seagrass conditions. Therefore, the availability of seagrass percent cover maps greatly assists in sustainable coastal ecosystem management. This research aimed to assess the consistency of PlanetScope imagery for seagrass percent cover mapping using two study areas, namely Parang Island and Labuan Bajo, Indonesia. Assessing the consistency of the PlanetScope imagery performance in seagrass percent cover mapping helps understand the effects of variations in the image quality on its performance in monitoring changes in seagrass cover. Percent cover maps were derived using object-based image analysis (image segmentation and random forest) and pixel-based random forest algorithm. Accuracy assessment and consistency analysis were conducted on the basis of the following three approaches: overall accuracy consistency, agreement percentage and consistent pixel locations. Results show that PlanetScope images can fairly consistently map seagrass percent cover for a specific area across different dates. However, these images produced different levels of accuracy when used for mapping in seagrass meadows with various characteristics and benthic cover complexities. The mapping accuracy (OA–overall accuracy) and consistency (AP–agreement percentage) in patchy seagrass meadows (Parang Island, mean OA 18.4%–38.6%, AP 44.1%–70.3%) are different from those in continuous seagrass meadows (Labuan Bajo, OA 43.0%–56.2%, and AP 41.8%–55.8%). Moreover, PlanetScope images are consistent when used for mapping seagrasses with low and high percent covers but strive to obtain good consistency for medium percent cover due to the combination of seagrass and non-seagrass in a pixel. Furthermore, images with relatively similar image acquisition conditions (i.e., winds, aerosol optical depth, signal-to-noise ratio, and sunglint intensity) produce better consistency. The OA is related to the image acquisition conditions, whilst the AP is related to variation in these conditions. Nevertheless, PlanetScope is still the best high spatial resolution image that provides daily acquisition and is highly beneficial for various applications in tropical areas with persistent cloud coverage. [ABSTRACT FROM AUTHOR]

Droughts may inflict significant damage to agricultural and water supplies, resulting in substantial financial losses as well as the death of people and livestock. This study intends to anticipate droughts by studying the changes of an acceptable index using appropriate climatic factors. This study was divided into three phases, first being the determination of the Standardized Precipitation Evapotranspiration (SPEI) index for the Cholistan, Punjab, Pakistan area based on a dataset spanning 1980 to 2020. The indices are calculated at different monthly intervals which could to predict short-term periods for the Cholistan in Pakistan, we selected two distinctive time periods of one month (SPEI–1) and three months (SPEI–3). The second phase involved dividing the data into three sample sizes, which were used for training data from 1980 to 2010, testing data from 2011 to 2015 and validation data from 2016 to 2020. The utilization of the random forest (RF) algorithm to train and evaluate the data using a variety of climate variables e.g. potential evapotranspiration, rainfall, vapor pressure cloud cover, and mean, minimum and maximum, temperature. The final phase was to analyze the performance of the model based on statistical metrics and drought classes. Based on these considerations, statistical measures, such as the Coefficient of Determination (R²) and the Root Mean Square Error (RMSE) approach, were used to evaluate the performance of the test group throughout the testing period. The model’s performance revealed the satisfactory results with R2 values of 0.80 and 0.78, for SPEI–1 and SPEI–3 situations, respectively. Following the data analysis, it was discovered that the validation period had a receiving operating curve and area under the Curve (ROC-AUC) of 0.87 for the SPEI–1 case and 0.85 for the SPEI–3 case. In this context, the results indicate that the SPEI may be useful as a prediction tool for drought prediction and the performances the RF model was suitable for both timescales. However, a more rigorous analysis with a larger dataset or a combination of datasets from different areas might be more beneficial for generalization over more extended time periods provide additional insights. [ABSTRACT FROM AUTHOR]

In this paper, an original methodology for landslide susceptibility mapping (LSM) is presented. It consists of bagging ensembles of artificial neural networks (ANNs) and random forests (RFs), and hybrid bagging ensembles of these models. It is applied on the area of the Itajaí-Açu river valley. In December 2020, there was an extreme rainfall in the region, which triggered landslides. The RF ensemble presented slightly higher accuracy (0.941) than the ANN ensemble (0.940), but the ANN ensemble had a more balanced relation between sensitivity (0.966) and specificity (0.915) than the RF ensemble (specificity = 0.992, sensitivity = 0.891). The mixed ANN-RF ensemble presented the higher accuracy of all (0.950), and a good balance between sensitivity (0.948) and specificity (0.951), being considered the best model within those analyzed. The hybrid ensemble, together with classification threshold adjustment, removed discrepancies on the maps between both models by attenuating them. [ABSTRACT FROM AUTHOR]

The purpose of this study is to develop a coupling model to improve the ability of random forest model to accurately predict karst collapse. Therefore, an inventory map consisting of 327 collapse points and 1962 non-collapse points was created. The database also contains 18 influencing factors, ranked with GeoDetector. 16 optimized factors were obtained. Bayesian algorithm was used to optimize the parameters of RF model. The optimized factors and RF model were used to create a collapse map, compared with the original map. After coupling and optimizing the factors and parameters, the accuracy of the RF model was 0.935; precision, 0.964, and AUC value, 0.977. Compared with the unoptimized model, the accuracy, precision and AUC value of the optimized RF model improved by 0.197, 0.146 and 0.134, respectively. The results show that the method of optimizing and coupling the factors and parameters contributes to improve the karst collapse susceptibility model. [ABSTRACT FROM AUTHOR]

The coarse resolutions of passive microwave surface soil moisture (SSM) products often hamper the applications of such products in regional or local studies. This study developed a machine learning-based approach for the downscaling of Soil Moisture Active and Passive (SMAP) SSM products at both ascending and descending passes based on the relationships between SSM and environmental variables, such as the land surface temperature (LST), enhanced vegetation index (EVI), surface albedo, cumulative precipitation, digital elevation model (DEM), and soil texture. Two machine learning algorithms—random forest (RF) and long shortterm memory network (LSTM)—were applied to downscale the SMAP product from a coarse resolution (36 km) to a fine resolution (1 km). The downscaled SSM results were validated against ground observations. The contributions of environmental variables to the established model were also discussed. The results showed that both RF and LSTM models demonstrated satisfactory performance in SMAP SSM prediction, indicating that the downscaling models were able to learn the relationships between the environmental variables and SMAP SSM well at coarse resolution. The RF and LSTM-based downscaled SSM maps not only realized full spatial coverage but also reasonably maintained the spatiotemporal evolution trends of the original SMAP SSM products. Both downscaled results correlated well with the ground observations and indicated good temporal consistency with the daily precipitation. In addition, the variable importance analysis reveals that the DEM, precipitation, EVI, and surface albedo were dominant to establishing SSM regression models, particularly for DEM in regions with large height differences. Overall, RF and LSTM-based models are promising downscaling approaches for generating full spatial coverage and fine-resolution SSM data from passive microwave SSM. [ABSTRACT FROM AUTHOR]

In this study, we aimed to explore the rural landscape transformation through the analysis of land use/land cover (LULC) spatiotemporal dynamics in the entire Vietnamese Mekong Delta over the three decades, using Landsat imageries and a supervised random forest classifier. Results indicated that in the 1990s, dominant LULC types were arable cropland, wetland, and permanent crops, which covered approximately half of the delta, 28% and 8%, respectively. From 1990 to 2019, the wetland area decreased from 28% to 5% due to the expansion of aquaculture and the arable cropland. The aquaculture, however, expanded more rapidly than other land use conversions, namely, from 2% to 19%. Although mangrove forests slightly recovered by 58 km² from 2005 to 2019, the overall trend (1990-2019) showed an intense loss of 740 km² due to widespread conversions into aquaculture. The paper unravels the complex dynamics between land-cover change, socio-economic development and associated land-use policies, which have significant implications for the change in rural landscapes. [ABSTRACT FROM AUTHOR]

Hyperspectral sensors have the potential of discerning subtle differences among wetland plant species. Assessment of wetland plant species is critical for the effective management of wetland ecosystems. We evaluated the utility of the forthcoming nSight-2 hyperspectral sensor in wetland plant species differentiation, by testing the utility of its spectral settings and compared its performance to EnMap and WorldView-2 sensors in classifying four dominant wetland plant species in Verloren Vallei Nature Reserve, South Africa. For this purpose, we used the Random Forest classifier and field spectrometer data of various wetland plant species. The results showed that the spectral settings of nSight-2, EnMap, and WorldView-2 yielded high overall accuracies of 84.09%, 81.82% and 77.77%, respectively. The best accuracies were achieved with spectral bands sampled across the visible, red-edge and near-infrared spectral regions. Overall, the findings demonstrate the potential of the upcoming hyperspectral satellite missions for wetland ecosystems monitoring and management. [ABSTRACT FROM AUTHOR]

Dengue Fever (DF) is a common vector-borne disease with catastrophic health implications. DF prediction modelling is a challenging task, although technologies such as Geographical Information Systems (GIS) and spatial statistics have improved our understanding of dengue dynamics. In this paper, we create a robust data analysis model to (i) provide a better understanding of confirmed dengue fever cases despite missing data, (ii) obtain better insights into risk factors associated with confirmed cases, and (iii) by means of machine learning, create clusters of patients with comparable characteristics. The last was accomplished with a self-organizing feature map (SOFM) and the densitybased spatial clustering of applications with noise (DBSCAN). The approaches used to classify confirmed cases were: Decision Tree, k-nearest neighbours, Random Forest, AdaBoost, Support Vector Classification (SVC), CatBoost, and Naive Bayes. The CatBoost classifier achieved the best accuracy for the analysis of confirmed cases. Spatial analysis was conducted using the ordinary least square (OLS) and geographically weighted regression (GWR) models to identify high-risk areas. SOM can group patients with similar features into clusters, then DBSCAN detects and retrieves six clusters from this data. The clustering of confirmed cases increases CatBoost’s modelling prediction accuracy and reveals complex factors that influence prediction accuracy. Because confirmed cases in each cluster have different features, CatBoost is applied to each cluster individually to improve the prediction accuracy. Variable values in each cluster are analysed to clarify the confirmed cases of a specific subset of DF incidents. Overall, OLS outperforms GWR when identifying hotspot areas. The proposed novel, data-driven and machine-learningbased strategy facilitates the understanding and identification of patterns associated with confirmed DF cases. The study’s findings can be utilized to cluster historical patient data into groups or subgroups sharing similar variables. Using identifiable patient clusters rather than raw history data improves the model accuracy provided by CatBoost. [ABSTRACT FROM AUTHOR]

Precise categorization of mangrove forests with medium spatial resolution satellite data is challenging and occasionally yields mixed outcomes. The available methods to estimate mangrove vegetation cover using moderately high-resolution images lack differentiation between mangrove and homestead vegetation. Mangrove vegetation displays a range of responses across the phenological cycle at different wavelengths of an optical sensor. Taking advantage of this principle, this study utilized some mangrove and non-mangrove vegetation indices (VIs) as predictor variables sourced from monthly Sentinel-2 data into the random forest algorithm to derive a phenology-based classification outcome. It also ascertained a suitable month for thresholding mangroves across different VIs. Results indicated that phenologybased classification with three classes was more accurate (95% overall accuracy) than threshold-based or WorldCover v100 classifications. MI and MVI layers from December image performed better in discerning mangroves. Findings have important implications in separating mangroves from other coastal vegetations. [ABSTRACT FROM AUTHOR]

Accurate distribution of irrigated, rainfed and paddy croplands is essential for food production and agricultural management. High spatial resolution land cover datasets rarely have detailed information about irrigated or rainfed croplands, while cropland datasets labelled with crop watering methods face challenges with coarse temporal and spatial resolution. This study proposed a semi-automatic detailed croplands mapping framework by integrating pixel-based classification and image segmentation. First, high-quality Sentinel-2 images were selected and mosaicked to time-series image dataset using Google Earth Engine platform. Second, pixel-based random forest classification and the Simple Non-Iterative Clustering image segmentation were integrated by optimal rules for generating 10-m resolution Detailed Croplands Map (DCM-2020). The DCM-2020 was assessed by using validation samples, and the overall accuracy of the map was 88.6% with kappa coefficient of 0.83. Compared with the existing cropland datasets, DCM-2020 shows much finer details, and croplands area is closer to official statistics. [ABSTRACT FROM AUTHOR]

Land-subsidence (LS) is a common geo-hazard in many regions of the world. The overexploitation of subsurface and ground water, followed by collapse of underground cavities, is one of the mechanisms that cause LS. Optimal prediction of LS is difficult due to limitations in monitoring, surveying and information about the mechanism and process of LS. Therefore, LS susceptibility mapping (LSSM) is crucial to prevent and reduce the economic damage of natural and manmade catastrophes. This study in the Isfahan Province, Iran, aimed to map LS susceptibility using a hybrid model of adaptive neuro-fuzzy inference system–genetic algorithm (ANFIS–GA) and three stand-alone machine-learning (ML) models: support vector machine, maximum entropy and ANFIS. In total, 155 LS historical points were collected, and 12 LS conditioning factors (LSCFs) were compiled for each site. These factors were elevation, slope, aspect, topographic wetness index, plan curvature, distance to stream, drainage density, groundwater withdrawal, lithology, distance to fault, normalized difference vegetation index and land use and land cover. These data were input into the models in five training-to-validation sample ratios, designated D1 (90:10), D2 (80:20), D3 (70:30), D4 (60:40) and D5 (50:50). The importance of these variables to the occurrence of LS was calculated using a random forest algorithm. Algorithm performance was evaluated through receiver operating characteristicarea under the curve analysis and the results show ANFIS–GA to be the optimal model, with average training and validation AUC values of 0.9644 and 0.9416, respectively. The results demonstrate that LSSMs can be effectively prepared to support decision makers in land use planning and allocation through the development of suitable management strategies. [ABSTRACT FROM AUTHOR]

The urban watershed of Guwahati is a highly flood-prone region and the fastest growing city situated on the bank of the Brahmaputra River. Therefore, this study aims to the urban flood susceptibility mapping of Guwahati city using metaheuristic optimization algorithms integrated with random forest (RF) machine learning algorithm. Further, the receiver operating characteristic (ROC) and multiple error measurements were applied to analyze the performances of the models used. The result showed that about one-third of the area of Guwahati city is under the high and very high flood risk while nearly 50% area comes under low and very low flood risk. The value of the area under curve (AUC) of ROC was above 0.80 for all the integrated models applied. However, the RF-bee colony (BCO) and the RF-based ant colony (ACO) are the two best flood susceptibility models that performed better in the analysis. The methodology adopted in the study is cost and time effective and can be used for the flood susceptibility modeling in other parts of the world. Further, the findings of this study can useful in the flood mitigation and planning process. [ABSTRACT FROM AUTHOR]

Flash flood can cause dramatic damages to the infrastructure of transportation networks. Because of the uncertainty of flash floods and the access function of roads, assessing the impact of flash floods on transportation systems has been a great challenge. In this study, we proposed a framework for evaluating the risk posed by flash floods to transportation network, which considers the interruption probability of road links and the expected impact on the access function of transportation. To assess the probability of interruption, we used the random forest model to output the flash floods susceptibility. Then, a multiple centrality model was used to evaluate the expected impact when a link was interrupted. The risk takes into account the flash floods susceptibility and road multiple centrality, and it identify critical links. Using the natural break points method, the result of flash floods susceptibility, road multiple centrality and risk were divided into five levels: extremely low, low, moderate, high and extremely high. Approximately 30.8% of the roads were found to be at high and extremely high risk, and most of these roads were located in Sichuan and Yunnan provinces. The flash floods susceptibility contributes more to the risk than the road multiple centrality, thus, further study should be focused on the areas with high flash floods susceptibility. We discussed different disaster prevention and mitigation measures for the different types of high risk links. The results can improve our understanding of the risks posed by flash floods to road networks. The proposed generalized network risk analysis method provides a new perspective and tool for analysing the impact of flash floods on road network. [ABSTRACT FROM AUTHOR]

This research introduces a scientific methodology to identify areas affected by gully erosion using Geographic Object Based Image Analysis (GEOBIA) and Random Forest (RF) supervised machine learning. The GEOBIA and RF were applied in Besni district, which has a Mediterranean climate, of Adiyaman province in Turkey by including many factors in the model. Estimation Scale Parameter (ESPII) algorithm was used in the segmentation phase. The novelty of this study is the implementation of RF supervised classification algorithm to classify a large number of objects determined after the segmentation process, due to the large size of the study area. Therefore, open access data has been evaluated with high classification accuracy without the need for labor. Precision, Recall and F1-Score values were calculated using true positive (TP), true negative (TN), false positive (FP) and false negative (FN) values based on field observations and Google Earth images of the study area. The TP, TN, FP and FN values were 0.90, 0.95 and 0.92, respectively. In addition, a Kappa-index was calculated as 0.88. The gully erosion map obtained using aforementioned methodology can be used to take necessary measures to prevent further degradation and plan sustainable land uses. [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]

Traditional crop cutting experiment-based yield estimation method captures the regional yield variability but lacks field-level information. Satellite images hold enormous crop information at finer spatial resolution. Crop yield mapping with optical images is particularly challenging if cloud-free images are unavailable during the crucial crop developmental stages. All-weather availability and sensitivity to crop structure, dielectric properties make synthetic aperture radar (SAR) images an excellent resource for yield estimation. Both types of data provide complementary information about crop conditions. A random forest regression model with genetic algorithm-based feature selection is developed to exploit the Sentinel-2 optical and Sentinel-1 SAR images for yield estimation. We utilized the crop harvest and quality survey (BEE) yield data set collected by the Hessisches Statistisches Landesamt (HSL), Wiesbaden, Germany, over 490 fields. We prepared 20m resolution yield maps for winter wheat, winter barley, winter rye and winter rapeseed. Input features for the yield estimation model are selected based on the prior knowledge of remote sensing of vegetation. Baseline random forest regression models are developed for all the four crop types with optical and SAR input features. An optimized random forest regression model with genetic algorithm-based feature selection results in performance improvement. Dissimilarity in genetic algorithm selected image features highlights the significance of crop-specific feature selection for yield estimation. The optimized models reliably estimate yield by achieving correlation coefficient (r) of 0.65-0.86, mean absolute error 0.93-1.16 t ha-1 and root mean square error 1.12-1.56 t ha-1 with BEE yield on testing data set. The proposed models could estimate the intra-field yield variation when winter wheat, winter barley, winter rye were in the shooting phase to the beginning of ear-shifting, and winter rapeseed began to flower or was already flowering. These results demonstrate the merits of our model for early-stage crop yield estimation at the field level with mono-temporal image and adaptability for the cropping season with high cloud cover. [ABSTRACT FROM AUTHOR]