Sentinel-2 Satellite Data Research Articles

Automatic detection of crop lodging from multitemporal satellite data based on the isolation forest algorithm

Rapid identification of crop lodging has implications for optimizing disaster prevention and mitigation measures. This study proposes a sequentially integrated algorithm for crop lodging identification, which first automatically extracts lodged and non-lodged samples based on the isolation forest algorithm from the screened features dataset and then uses a supervised classifier for lodging identification. Taking the crop lodging disaster caused by the super typhoon “Maysak” in Bohetai Township as an example, we calculated 162 feature indices from Sentinel-1 and Sentinel-2 satellite data pre- and post-disaster and screened the optimal features. Then, the abnormal scores of the cultivated-land pixels were calculated using the isolation forest algorithm. After that, we calculated the coefficient of variation (CV) of the abnormal scores of each group, extracted the lodged and non-lodged samples based on the cumulative CV contribution rate, and input samples into three supervised classifiers (random forest, maximum likelihood, and support vector machine) to identify lodged crop pixels. The results showed that feature screening increased the identification accuracy of crop lodging by more than 10% and difference features of short-wave infrared (SWIR) and red edge bands contributed significantly to the identification. The accuracy of crop lodging automatic identification was verified using samples obtained from visual interpretation and digitization of UAV images as reference data and the overall accuracy reached 78%. The proposed method can simultaneously recognize lodging of different crop types without the need to select lodged samples and extract lodged ranges for each crop. With low data acquisition costs and high automation, the proposed method has promising applications in agricultural disaster emergency management and agricultural insurance loss assessment.

Assessing damage to agricultural fields from military actions in Ukraine: An integrated approach using statistical indicators and machine learning

The ongoing full-scale Russian invasion of Ukraine has led to widespread damage of agricultural lands, jeopardizing global food security. Timely detection of impacted fields enables quantification of production losses, guiding recovery policies and monitoring military actions. This study presents a robust methodology to automatically identify agricultural areas damaged by wartime ground activities using free Sentinel-2 satellite data. The 10 m resolution spectral bands and vegetation indices are leveraged, alongside their statistical metrics over time, as inputs to a Random Forest classifier. The algorithm efficiently pinpoints damaged fields, with accuracy metrics around 0.85. Subsequent anomaly detection delineates damages within the fields by combining spectral bands and indices. Applying the methodology over 22 biweekly periods in 2022, approximately 500 thousand ha of cropland across 10 regions of Ukraine were classified as damaged, with the most significant impacts occurring from March to September. The algorithm provides updated damage information despite cloud cover and vegetation shifts. The approach demonstrates the efficacy of automated satellite monitoring to assess agricultural impacts of military actions, supporting recovery analysis and documentation of war crimes.

Forest biomass assessment combining field inventorying and remote sensing data

Abstract Forests offer high potential for the fight against climate change. However, forests are faced with increased deforestation. REDD+ is a financial mechanism that offers hope to developing countries for tackling deforestation. Aboveground (AGB) estimation, however, is necessary for such financial mechanisms. Remote sensing methods offer various advantages for AGB estimation. A study, therefore, was conducted for the estimation of AGB using a combination of remote sensing Sentinel-1 (S1) and Sentinel-2 (S2) satellite data and field inventorying. The mean AGB for Sub-tropical Chir Pine Forest was recorded as 146.73 ± 65.11 Mg ha−1, while for Sub-tropical Broadleaved Evergreen Forest it was 33.77 ± 51.63 Mg ha−1. Results revealed weak associations between the S1 and S2 data with the AGB. Nonetheless, S1 and S2 offer advantages such as free data resources that can be utilized by developing countries for forest biomass and carbon monitoring.

Harnessing the Power of Remote Sensing and Unmanned Aerial Vehicles: A Comparative Analysis for Soil Loss Estimation on the Loess Plateau

This study explored the innovative use of multiple remote sensing satellites and unmanned aerial vehicles to calculate soil losses in the Loess Plateau of Iran. This finding emphasized the importance of using advanced technologies to develop accurate and efficient soil erosion assessment techniques. Accordingly, this study developed an approach to compare sinkholes and gully heads in hilly regions on the Loess Plateau of northeast Iran using convolutional neural network (CNN or ConvNet). This method involved coupling data from UAV, Sentinel-2, and SPOT-6 satellite data. The soil erosion computed using UAV data showed AUC values of 0.9247 and 0.9189 for the gully head and the sinkhole, respectively. The use of SPOT-6 data in gully head and sinkhole computations showed AUC values of 0.9105 and 0.9123, respectively. The AUC values were 0.8978 and 0.9001 for the gully head and the sinkhole using Sentinel-2, respectively. Comparison of the results from the calculated UAV, SPOT-6, and Sentinel-2 data showed that the UAV had the highest accuracy for calculating sinkhole and gully head soil features, although Sentinel-2 and SPOT-6 showed good results. Overall, the combination of multiple remote sensing satellites and UAVs offers improved accuracy, timeliness, cost effectiveness, accessibility, and long-term monitoring capabilities, making it a powerful approach for calculating soil loss in the Loess Plateau of Iran.

Crop Yield Assessment Using Field-Based Data and Crop Models at the Village Level: A Case Study on a Homogeneous Rice Area in Telangana, India

Crop yield estimation has gained importance due to its vital significance for policymakers and decision-makers in enacting schemes, ensuring food security, and assessing crop insurance losses due to biotic and abiotic stress. This research focused on rice yield estimation at the field level in the Karimnagar district of Telangana during 2021 and 2022 by employing the leaf area index (LAI) as the primary criterion for integrating remote sensing technology and crop simulation models. Using Sentinel-2 satellite data, the rice crop was mapped with the help of ground data and machine learning algorithms, attaining an accuracy of 93.04%. Crop management data for the DSSAT tool were collected during the field visits; the model results revealed a 0.80 correlation between observed and predicted yields. Due to its strong correlation with LAI (0.82), the normalized difference vegetation index (NDVI) was selected as the critical element for integration with the model. A spatial LAI map was generated using the linear equation developed between the NDVI and LAI. The relationship between LAI and yield was used to create a spatial yield map. The study’s findings show that assimilating remote sensing data with crop models enhances the precision of rice yield prediction for insurance companies and policy- and decision-makers.

Enhancing Water Depth Estimation from Satellite Images Using Online Machine Learning: A Case Study Using Baidu Easy-DL with Acoustic Bathymetry and Sentinel-2 Data

Water depth estimation is paramount in various domains, including navigation, environmental monitoring, and resource management. Traditional depth measurement methods, such as bathymetry, can often be expensive and time-consuming, especially in remote or inaccessible areas. This study delves into the application of machine learning techniques, specifically focusing on the Baidu Easy DL model for water depth estimation leveraging satellite imagery. Utilizing Sentinel-2 satellite data over Rushikonda Beach in India and processing it into remote sensing reflectance using ACOLITE software, this research compares the performance of several machine learning algorithms, including the Stumpf model, Log-Linear model, and the Baidu Easy DL model, for accurate depth estimation. The results indicate that the Easy-DL model outperforms traditional methods, particularly excelling in the 0–11 m depth range. This study showcases the substantial potential of machine learning in remote sensing, offering robust water depth estimates, even in complex coastal environments. Furthermore, it underscores the critical role of comprehensive training datasets and ensemble learning techniques in enhancing accuracy. This research opens avenues for the further exploration of machine learning applications in remote sensing and highlights the promising prospects of online model APIs when streamlining remote sensing data processing.

The seismic hazard from the Lembang Fault, Indonesia, derived from InSAR and GNSS data

Abstract. A growing number of large cities are located near poorly understood faults that have not generated a significant earthquake in recent history. The Lembang Fault is one such fault located near the city of Bandung in West Java, Indonesia. The slip rate on this fault is debated, with estimates ranging from 6 to 1.95–3.45 mm yr−1, derived from a GNSS (global navigation satellite system) campaign and geological measurements respectively. In this paper we measure the surface deformation across the Bandung region and resolve the slip rate across the Lembang Fault using radar interferometry (InSAR – interferometric synthetic aperture radar) analysis of 6 years of Sentinel-1 satellite data and continuous GNSS measurements across the fault. Our slip rate estimate for the fault is 4.7 mm yr−1, with the shallow portions of the fault creeping at 2.2 mm yr−1. Previous studies estimated the return period of large earthquakes on the fault to be between 170–670 years. Assuming simplified fault geometries and a reasonable estimate of the seismogenic depth we derive an estimated moment deficit equivalent to magnitude 6.6–7.0 earthquakes, indicating that the fault poses a very real hazard to the local population. Using the Global Earthquake Model OpenQuake engine we calculate ground motions for these two earthquake scenarios and estimate that 1.9–2.7 million people within the Bandung metropolitan region would be exposed to ground shaking greater than 0.3 g. This study highlights the importance of identifying active faults, understanding their past activity, and measuring the current strain rates of smaller crustal active faults located near large cities in seismic zones.

Change Monitoring and Forest Density Classification of Gir Wildlife Sanctuary, India

In India we found a main 5 types forest classification. As India covers the 21.7% of the total land in Forest. Forest are the main and most important ecosystem on earth without forest there is impossible for any creature to survive on earth, because almost 70% of the resources are obtained from the forest. In this research we have study the forest change monitoring of the Gir sanctuary in Saurashtra district of Gujarat. The forest of Gir sanctuary is Dry deciduous forest. As this district covers the main portion of the forest cover in Gujarat state. With the help of remote sensing and GIS we can easily monitor the change monitoring and forest density change in the area by taking the 20 years difference 1999 to 2019. This study identifies the change monitoring and density classification in the Gir wildlife sanctuary and we have also taken 40 km buffer zone near the sanctuary. It was observed that there is increase in the forest cover while comparing the images of Sentinel-2 (1999) and landsat-5 satellite data (2019) of the study area that the Forest cover since the year 1999 has increased with an increase in Forest density. There is an increase in the human population in the 40 kilometres buffer zone. This human population is mainly dependent on the agriculture and animal husbandry business. An increase in the livestock population may also increase the issue of overgrazing. Plus, the conflict of wildlife with the livestock may also harm the wildlife. Hence government must look in the issue of increasing human population near the sanctuary area.

Information technologies of simulation of beam structures using multispectral spacecraft materials

The work is devoted to solving the scientific and practical task of modeling beam structures based on the materials of multispectral space images based on aerospace and contact measurements. The effectiveness of the use of space survey materials for the study of soil cover largely depends on the time of the survey. The linear forms of erosion (waterholes, ravines) are deciphered on space photographs, which are displayed only on images with a spatial resolution of 1-2 meters in the form of narrow, clearly delineated contours that have a jagged shape.The developed clustering algorithm makes it possible to more clearly identify beam structures on satellite images in combination with data from digital terrain models (DRM). A number of experiments were conducted on some set of remote sensing data of Boryspil and c. Panchevo, Novoukrainsky District, Kirovohrad Region. The experiments consisted in determining the spectral and other features of the beam structures (for example, the shape, soil types, etc.), which are located in different places of the territory that was investigated.On images with a spatial resolution of more than 10 meters, ravines are usually not displayed, but networks of beams with elongated wavy tree-like shapes are clearly visible. In the course of the study, data from multispectral imaging from the Sentinel-2 satellite (MSI scanner) and DEM (Digital Elevation Model, DEM) data obtained through the SRTM 3 archive were used.The research results showed that automating the process of highlighting beam structures on multispectral images with a spatial resolution of 30 m is very difficult. First of all, this can be explained by the fact that the beam consists of vegetation that is also present outside the beam. In addition, the number of channels of the ETM+ scanner and its spatial ability are not enough for a clearer separation of the "beam" class.

Extraction and geospatial analysis of the Hersek Lagoon shoreline with Sentinel-2 satellite data

In this study, the coastal changes in Hersek Lagoon, have occurred in the 5 years (2015 to 2020) were examined. With the Modified Normalised Difference Water Index (MNDWI), the water areas in the lagoon were determined by object-based classification. When the changes are examined on a regional basis, it is seen that there are erosion and accretion areas were observed. Pearson's r value was examined between End Point Rate (EPR) and Linear Regression Rate (LRR) and a high correlation such as r = 0.921 was obtained. The maximum coastal change was observed as 18.74 m/year with EPR and 18.62 m/year with LRR.

The geochemistry, origin, and hydrothermal alteration mapping associated with the gold-bearing quartz veins at Hamash district, South Eastern Desert, Egypt

Integrating diverse techniques and datasets, significantly enhances the accurate identification of various mineral deposits. This work aims to determine different types of mineral deposits in the Hamash district (Southern Eastern Desert, Egypt) by combining structural features (derived from ALOS PALSAR DEM), alteration zones (detected using ASTER and Sentinel-2), and ore mineralogy. Multispectral imaging, such as ASTER and Sentinel-2 satellite data, provides a cost-effective and efficient tool for lithological and hydrothermal alteration mapping utilizing selective band ratios (SBR), directed principal component analysis (DPCA), feature-oriented false-color composites (FFCC), and constrained energy minimization (CEM). The deductions drawn from the analysis of ASTER and Sentinel 2 satellite data are solidly corroborated through meticulous investigations of pre-existing lithological maps in the study area, on-site validation via fieldwork, and robust laboratory analysis, attesting to reliable results. Validation of remote sensing results was performed through field observations, petrographic investigations, X-ray diffraction technique (XRD), and SEM–EDX analyses. Based on ore mineralogy derived from XRD and SEM results the quartz-vein-associated ore minerals in the Hamash district include chalcopyrite, pyrite, hematite, goethite, bornite, covellite, and gold. According to the present paragenesis, the mineralization in the study area is classified into three types: sulfide mineralized zone, transitional zone, and supergene zone. Using an ore microscope, our studies identified that the alteration zones include gold-bearing sulfide minerals as well as the minerals goethite and malachite. In gold-bearing quartz samples, the concentrations of Cu, As, Ag, and Sb are positively correlated with Au at the degree of shear deformation. According to data gathered from the fire assay results, Au content varied from 0.027 to 57.20 ppm, along with Cu (10–6484 ppm), Ag (0.5–20.5 ppm), As (5–2046 ppm), Zn (3–1095 ppm), Pb (2–1383 ppm), and Sb (5–23). Our results confirmed that the Hamash region is one of the most important gold-bearing sites, with gold concentrations ranging from 0.027 up to 57.20 ppm. Furthermore, the current contribution highlighted four stages in the paragenetic sequence of the recorded ores, including magmatic, metamorphic, hydrothermal, and supergene by origin, indicating a considered similarity with the known Egyptian gold sites regarding host rocks, mineralization style, alteration assemblage, and several ore mineral conditions.

Finding Misclassified Natura 2000 Habitats by Applying Outlier Detection to Sentinel-1 and Sentinel-2 Data

The monitoring of Natura 2000 habitats (Habitat Directive 92/43/EEC) is a key activity ensuring the sufficient protection of European biodiversity. Reporting on the status of Natura 2000 habitats is required every 6 years. Although field mapping is still an indispensable source of data on the status of Natura 2000 habitats, and very good field-based data exist in some countries, keeping the field-based habitat maps up to date can be an issue. Remote sensing techniques represent an excellent alternative. Here, we present a new method for detecting habitats that were likely misclassified during the field mapping or that have changed since then. The method identifies the possible habitat mapping errors as the so-called “attribute outliers”, i.e., outlying observations in the feature space of all relevant (spectral and other) characteristics of an individual habitat patch. We used the Czech Natura 2000 Habitat Layer as field-based habitat data. To prepare the feature space of habitat characteristics, we used a fusion of Sentinel-1 and Sentinel-2 satellite data along with a Digital Elevation Model. We compared outlier ratings using the robust Mahalanobis distance and Local Outlier Factor using three different thresholds (Tukey rule, histogram-based Scott’s rule, and 95% quantiles in χ2 distribution). The Mahalanobis distance thresholded by the 95% χ2 quantile achieved the best results, and, because of its high specificity, appeared as a promising tool for identifying erroneously mapped or changed habitats. The presented method can, therefore, be used as a guide to target field updates of Natura 2000 habitat maps or for other habitat/land cover mapping activities where the detection of misclassifications or changes is needed.

A method for estimating yield of maize inbred lines by assimilating WOFOST model with Sentinel-2 satellite data.

Maize is the most widely planted food crop in China, and maize inbred lines, as the basis of maize genetic breeding and seed breeding, have a significant impact on China's seed security and food safety. Satellite remote sensing technology has been widely used for growth monitoring and yield estimation of various crops, but it is still doubtful whether the existing remote sensing monitoring means can distinguish the growth difference between maize inbred lines and hybrids and accurately estimate the yield of maize inbred lines. This paper explores a method for estimating the yield of maize inbred lines based on the assimilation of crop models and remote sensing data, initially solves the problem. At first, this paper analyzed the WOFOST(World Food Studies)model parameter sensitivity and used the MCMC(Markov Chain Monte Carlo) method to calibrate the sensitive parameters to obtain the parameter set of maize inbred lines differing from common hybrid maize; then the vegetation indices were selected to establish an empirical model with the measured LAI(Leaf Area Index) at three key development stages to obtain the remotely sensed estimated LAI; finally, the yield of maize inbred lines in the study area was estimated and mapped pixel by pixel using the EnKF(Ensemble Kalman Filter) data assimilation algorithm. Also, this paper compares a method of assimilation by setting a single parameter. Instead of the WOFOST parameter optimization process, a parameter representing the growth weakness of the inbred lines was set in WOFOST to distinguish the inbred lines from the hybrids. The results showed that the yield estimated by the two methods compared with the field measured yield data had R2: 0.56 and 0.18, and RMSE: 684.90 Kg/Ha and 949.95 Kg/Ha, respectively, which proved that the crop growth model of maize inbred lines established in this study combined with the data assimilation method could initially achieve the growth monitoring and yield estimation of maize inbred lines.

Soil Salinity Estimation for South Kazakhstan Based on SAR Sentinel-1 and Landsat-8,9 OLI Data with Machine Learning Models

Climate change, uneven distribution of water resources and anthropogenic impact have led to salinization and land degradation in the southern regions of Kazakhstan. Identification of saline lands and their mapping is a laborious process associated with a complex of ground measurements. Data from remote sensing are widely used to solve this problem. In this paper, the problem of assessing the salinity of the lands of the South Kazakhstan region using remote sensing data is considered. The aim of the study is to analyze the applicability of machine learning methods to assess the salinity of agricultural lands in southern Kazakhstan based on remote sensing. The authors present a salinity dataset obtained from field studies and containing more than 200 laboratory measurements of soil salinity. Moreover, the authors describe the results of applying several regression reconstruction algorithms (XGBoost, LightGBM, random forest, Support vector machines, Elastic net, etc.), where synthetic aperture radar (SAR) data from the Sentinel-1 satellite and optical data in the form of spectral salinity indices are used as input data. The obtained results show that, in general, these input data can be used to estimate salinity of the wetted arable land. XGBoost regressor (R2 = 0.282) showed the best results. Supplementing the radar data with the values of salinity spectral index improves the result significantly (R2 = 0.356). For the local datasets, the best result shown by the model is R2 = 0.473 (SAR) and R2 = 0.654 (SAR with spectral indexes), respectively. The study also revealed a number of problems that justify the need for a broader range of ground surveys and consideration of multi-year factors affecting soil salinity. Key results of the article: (i) a set of salinity data for different geographical zones of southern Kazakhstan is presented for the first time; (ii) a method is proposed for determining soil salinity on the basis of synthetic aperture radar supplemented with optical data, and this resulted in the improved prediction of the results for the region under consideration; (iii) a comparison of several types of machine learning models was made and it was found that boosted models give, on average, the best prediction result; (iv) a method for optimizing the number of model input parameters using explainable machine learning is proposed; (v) it is shown that the results obtained in this work are in better agreement with ground-based measurements of electrical conductivity than the results of the previously proposed global model.

Machine learning-ready remote sensing data for Maya archaeology

In our study, we set out to collect a multimodal annotated dataset for remote sensing of Maya archaeology, that is suitable for deep learning. The dataset covers the area around Chactún, one of the largest ancient Maya urban centres in the central Yucatán Peninsula. The dataset includes five types of data records: raster visualisations and canopy height model from airborne laser scanning (ALS) data, Sentinel-1 and Sentinel-2 satellite data, and manual data annotations. The manual annotations (used as binary masks) represent three different types of ancient Maya structures (class labels: buildings, platforms, and aguadas – artificial reservoirs) within the study area, their exact locations, and boundaries. The dataset is ready for use with machine learning, including convolutional neural networks (CNNs) for object recognition, object localization (detection), and semantic segmentation. We would like to provide this dataset to help more research teams develop their own computer vision models for investigations of Maya archaeology or improve existing ones.

Mapping cover crop species in southeastern Michigan using Sentinel-2 satellite data and Google Earth Engine.

Cover crops are a critical agricultural practice that can improve soil quality, enhance crop yields, and reduce nitrogen and phosphorus losses from farms. Yet there is limited understanding of the extent to which cover crops have been adopted across large spatial and temporal scales. Remote sensing offers a low-cost way to monitor cover crop adoption at the field scale and at large spatio-temporal scales. To date, most studies using satellite data have mapped the presence of cover crops, but have not identified specific cover crop species, which is important because cover crops of different plant functional types (e.g., legumes, grasses) perform different ecosystem functions. Here we use Sentinel-2 satellite data and a random forest classifier to map the cover crop species cereal rye and red clover, which represent grass and legume functional types, in the River Raisin watershed in southeastern Michigan. Our maps of agricultural landcover across this region, including the two cover crop species, had moderate to high accuracies, with an overall accuracy of 83%. Red clover and cereal rye achieved F1 scores that ranged from 0.7 to 0.77, and user's and producer's accuracies that ranged from 63.3% to 86.2%. The most common misclassification of cover crops was fallow fields with remaining crop stubble, which often looked similar because these cover crop species are typically planted within existing crop stubble, or interseeded into a grain crop. We found that red-edge bands and images from the end of April and early July were the most important for classification accuracy. Our results demonstrate the potential to map individual cover crop species using Sentinel-2 imagery, which is critical for understanding the environmental outcomes of increasing crop diversity on farms.

Mapping Cropland Soil Nutrients Contents Based on Multi-Spectral Remote Sensing and Machine Learning

Nitrogen (N) and phosphorus (P) are primary indicators of soil nutrients in agriculture. Accurate management of these nutrients is essential for ensuring food security. High-resolution, multi-spectral remote sensing images can provide crucial information for mapping soil nutrients at the field scale. This study compares the capabilities of ZH-1 and Sentinel-2 satellite data, along with different spectral indices, in mapping soil nutrients (total N and Olsen-P) using two machine learning algorithms, random forest (RF) and XGBoost (XGB). Two agricultural fields in Suihua City were selected as the study areas for this investigation. The results showed that Sentinel-2 data performed best in computing the total N content in soil using the RF model (R2 = 0.74, RMSE = 0.10 g/kg). However, for the soil Olsen-P content, the XGBoost model performed better with ZH-1 data (R2 = 0.75, RMSE = 9.79 mg/kg) than the RF model. This study demonstrates that both ZH-1 and Sentinel-2 satellite data perform well in terms of accurately mapping soil total N and Olsen-P contents using machine learning. Due to its higher spectral and spatial resolution, ZH-1 remote sensing data provides more detailed information on soil nutrient content during Olsen-P inversion and exhibits comparable accuracy.

Sensitivity Evaluation of Time Series InSAR Monitoring Results for Landslide Detection

Spaceborne interferometric synthetic aperture radar (InSAR) techniques are important for landslide detection and monitoring; however, several limitations and uncertainties, such as the unique north–south flying direction and side-look radar observing geometry, currently limit the ability of InSAR to credibly detect landslides, especially those related to high and steep slopes. Here, we conducted experimental and statistical analysis on the feasibility of time-series InSAR monitoring for steep slopes using ascending and descending SAR images. First, the theoretical (TGNSS), practical (PGNSS), and terrain (Hterrain) (T-P-H) indices for sensitivity evaluations of the slope displacement monitoring results from time-series InSAR were proposed for slope monitoring. Subsequently, two experimental and statistical studies were conducted for the cases with and without Global Navigation Satellite System (GNSS) monitoring data. Our experimental results of two high and steep open-pit mines showed that the defined theoretical and practical sensitivity indices can quantitatively evaluate the feasibility of ascending and descending InSAR observations in steep-slope deformation monitoring with GNSS data, and the terrain sensitivity index can qualitatively evaluate the feasibility of landslide monitoring results from ascending and descending Sentinel-1 satellite data without GNSS data. We further demonstrate the generalizability of these proposed indices using four landslide cases with both public GNSS and InSAR monitoring data and 119 landslide cases with only InSAR monitoring data. The statistical results indicated that greater indices correlated with higher reliability of the monitoring results, suggesting that these novel indices have wide suitability and applicability. This study can help to improve the practice of slope deformation monitoring using spaceborne InSAR, especially for high and steep slopes.

Spatial Flood Forecasting Modeling under Lack of Data Using RS and Optimized Support Vector Machine: A Case Study of the Zahedan Watershed

This research was conducted with the aim of producing flood susceptible area maps of the Zahedan catchment in Iran during lack of data using remote sensing. To determine the factors to be included in the model, factors identified in previous studies were prepared using remote sensing and were evaluated by the information gain ratio (IGR) method and the multicollinearity diagnostic test, and ultimately 10 factors with the highest IGR values were chosen as the most effective factors in the region. The flood inventory map was produced by processing the Sentinel-1 satellite data. The gathered data were used to map flood susceptibility maps with the SVM model optimized with IWO and ACO. The prediction accuracy of the models was evaluated in terms of root mean square error (RMSE), mean absolute error (MAE), and the area under the receiver operating characteristic (ROC) curve (AUC). While both optimization algorithms are effective in improving the performance of SVM, the hybrid of SVM with IWO shows the best performance in terms of statistical measures and Friedman test results. The results of the study confirm the good performance of the proposed models in spatial prediction of flood susceptible areas. Since over half of the urban lands of the city of Zahedan are at moderate to very high risk of flooding, this area needs more attention in terms of flood prevention and control measures.

MP-Net: An efficient and precise multi-layer pyramid crop classification network for remote sensing images

Accurate crop classification map is of great significance in various fields such as the survey of agricultural resource, the analysis of existing circumstance on land application, the yield estimation of crop and the disaster warning. The methods based on machine learning and deep learning are popularly used in crop classification and recognition of remote sensing images. However, the crop classification task based on neural networks still faces significant challenges due to the spatial and temporal distribution of crops and the inherent characteristics of remote sensing images. Therefore, this study proposes the multi-layer pyramid crop classification network (MP-Net) to solve the above problems. To reduce the feature loss during the crop extraction, the proposed model uses the pyramid pooling module to improve the ability of global information acquisition, and the information concatenation module to retain the upper features. Using the GF-6 and Sentinel-2 satellite data, the proposed model was tested in Erhai Lake Basin and Beian City. Compared with other five deep learning models, such as FCN, SegNet, U-Net, PSPNet and DeepLabv3+, the experimental results indicate that the proposed model achieves the highest accuracy in both study areas. Meanwhile, the proposed model has the advantages of short training time and high efficiency under the same running conditions. Overall, this study is beneficial to improve the efficiency and accuracy of crop classification task in the unbalanced temporal and spatial distribution. It also brings a feasible scheme for crop classification tasks in complex growing areas. The code has been publicly available at https://github.com/Xu-Chang-Hong/MP-Net.