Remote Sensing Data Research Articles

Enhanced root zone soil moisture monitoring using multitemporal remote sensing data and machine learning techniques

Accurate root zone soil moisture (RZSM) estimation using remote sensing (RS) in areas with dense vegetation is essential for real-time field monitoring and precise irrigation scheduling. Traditional methods often face challenges due to the dense crop cover and the complexity of soil and climate interactions. These challenges include the coarse spatial resolution of available soil moisture products, the influence of vegetation and surface roughness, and the difficulty of estimating RZSM from surface data. Aiming to overcome these limitations, two RZSM estimation methods were developed by combining synthetic aperture radar (SAR) data from Sentinel-1 (VV and VH polarizations) and optical and thermal RS data from Landsat-8. These data sources were used in conjunction with various machine learning (ML) models such as M5-pruned (M5P), support vector regression (SVR), extreme gradient boosting (XGBoost), and random forest regression (RFR) to improve the accuracy of soil moisture estimation. In addition to RS data, soil physical and hydraulic properties, meteorological variables, and topographical parameters were selected as inputs to the ML models for estimating the RZSM of sugarcane crops in Khuzestan, Iran. This study identified the temperature vegetation dryness index (TVDI) as a critical parameter for estimating RZSM in combination with the Sentinel-1 SAR data under high vegetation conditions. In both methods, the RFR algorithm outperformed, with similar performance, the XGBoost, SVR, and M5P algorithms in estimating soil surface moisture (R2 = 0.89, RMSE = 0.04 cm3cm−3). However, the accuracy of the RFR algorithm decreased with increasing depth for both the optical-thermal and combined SAR and optical-thermal RS data. This decrease was more pronounced in the combined approach, particularly for the root zone, where the RMSE reached approximately 0.073 cm3cm−3. Accordingly, the key findings demonstrated that the optical-thermal RS data outperformed the SAR RS data for retrieving RZSM in high-vegetated areas. However, combining TVDI with SAR data is a substantial improvement that opens a new path in radar-based RZSM estimation methods under high vegetation conditions.

Integrating Active and Passive Remote Sensing Data for Forest Age Estimation in Shangri-La City, China

The accurate mapping of age structure and access to spatially explicit information are essential to optimal planning and policy-making for forest ecosystems, including forest management and sustainable economic development. Specifically, surveying and mapping the age structure of forests is crucial for calculating the carbon sequestration capacity of forest ecosystems. However, spatial heterogeneity and limited accessibility make forest age mapping in mountainous areas challenging. Here, we present a new workflow using ICESat-2 LiDAR data integrated with multisource remote sensing imagery to estimate forest age in Shangri-La, China. Two methods—a climate-driven exponential model and a random forest algorithm—are compared to infer the age structure of the five dominant species in Shangri-La. The climate-driven model, with an R2 of 0.67 and an RMSE of 12.79 years, outperforms the random forest model. The derived wall-to-wall forest age map at 30 m resolution reveals that nearly all forests in Shangri-La are mature or overmature, especially among the high-elevation species Abies fabri (Mast.) Craib and Picea asperata Mast., compared with Pinus yunnanensis Franch., Quercus aquifolioides Rehd. and E.H. Wils. and Pinus densata Mast., where the age structure is more evenly distributed across different elevation ranges. Younger forests are frequently found around human settlements and along the Jinsha River valley, whereas older forests are located in remote and high-elevation areas that are less disturbed. The combined use of active and passive remote sensing data has resulted in substantial improvements in the spatial detail and accuracy of wall-to-wall age mapping, which is expected to be a cost-effective approach for supporting forest management and carbon accounting in this important ecological region. The method developed here can be scaled to other mountain areas both to understand the age patterns and structure of mountain forests and to provide critical information for forestation, reforestation and carbon accounting in surface-to-high mountain areas, which are increasingly crucial for climate mitigation.

Remote sensing and big data: Google Earth Engine data to assist calibration processes in hydro-sediment modeling on large scales

Mathematical modeling aids in understanding large-scale erosion and sedimentation. However, sediment transport models calibration is constrained by data scarcity. This study explores the use of remote sensing (RS) imagery to supplement observed data, addressing three key questions: (1) How can high-resolution RS data be obtained using cloud-based methods for hydro-sediment applications, considering river changes? (2) What are the benefits of RS data in data-scarce conditions? (3) How can RS data improve hydro-sediment modeling in data-deficient regions? We developed a method to acquire large-scale RS data using Google Earth Engine (GEE) to obtain red and infrared reflectance from satellite imagery. After filtering errors, the data were used to calibrate a hydro-sediment model. Results showed that RS data, when combined with observed data, provided similar outcomes but performed better for lower values. Calibration with RS data alone improved the Kling-Gupta Efficiency (KGE) by 5%–18% and correlation by 5%–15%. Key conclusions are: (I) Cloud-based calibration is superior to using limited virtual stations; (II) RS data effectively complements observed data in hydro-sediment modeling; (III) Calibration using only RS data is beneficial in ungauged basins and preferable to no calibration.

Comparative study of evapotranspiration from the SWAT model and MODIS-derived remote-sensing data in two climatic zones in Egypt

ABSTRACT Evapotranspiration (ET) estimation is highly dependent on several input factors that differ between different estimation methods either from models or remote-sensing data. Therefore, the main objectives of this study are to assess and compare the ET simulated from the SWAT model and derived from MODIS (SSEBop and MOD16A2) in South-Delta (northern Egypt) and KomOmbo (southern Egypt) zones during the period from April 2013 to December 2020. The daily rainfall, maximum temperature (Tmax), minimum temperature (Tmin), solar radiation (Rs), relative humidity (RH), and wind speed (WND) from the NASA-POWER agroclimatology dataset were used to run the SWAT model. The results showed that the simulated monthly, seasonal, and annual ET from SWAT is lower than SSEBop by about −41% in South-Delta and −66% in KomOmbo and higher than MOD16A2 by about 34% in South-Delta and 28% in KomOmbo. The SWAT model may have the potential to produce reasonable ET values, as it is reliant on both climatic and actual land-surface conditions. The monthly and seasonal ET from SWAT and MODIS is positively correlated with Rs, Tmax, Tmin, and WND, and is negatively correlated with RH and rainfall, while the annual ET has varied (positive/negative) weak correlation with the weather variables.

Relationship between Vegetation and Soil Moisture Anomalies Based on Remote Sensing Data: A Semiarid Rangeland Case

Relationship between Vegetation and Soil Moisture Anomalies Based on Remote Sensing Data: A Semiarid Rangeland Case

Boosting cross-modal retrieval in remote sensing via a novel unified attention network

With the rapid advent and abundance of remote sensing data in different modalities, cross-modal retrieval tasks have gained importance in the research community. Cross-modal retrieval belongs to the research paradigm in which the query is of one modality and the retrieved output is of the other modality. In this paper, the remote sensing (RS) data modalities considered are the earth observation optical data (aerial photos) and the corresponding hand-drawn sketches. The main challenge of the cross-modal retrieval research objective for optical remote sensing images and the corresponding sketches is the distribution gap between the shared embedding space of the modalities. Prior attempts to resolve this issue have not yielded satisfactory outcomes regarding accurately retrieving cross-modal sketch-image RS data. The state-of-the-art architectures used conventional convolutional architectures, which focused on local pixel-wise information about the modalities to be retrieved. This limits the interaction between the sketch texture and the corresponding image, making these models susceptible to overfitting datasets with particular scenarios. To circumvent this limitation, we suggest establishing multi-modal correspondence using a novel architecture of the combined self and cross-attention algorithms, SPCA-Net to minimize the modality gap by employing attention mechanisms for the query and other modalities. Efficient cross-modal retrieval is achieved through the suggested attention architecture, which empirically emphasizes the global information of the relevant query modality and bridges the domain gap through a unique pairwise cross-attention network. In addition to the novel architecture, this paper introduces a unique loss function, label-specific supervised contrastive loss, tailored to the intricacies of the task and to enhance the discriminative power of the learned embeddings. Extensive evaluations are conducted on two sketch-image remote sensing datasets, Earth-on-Canvas and RSketch. Under the same experimental conditions, the performance metrics of our proposed model beat the state-of-the-art architectures by significant margins of 16.7%, 18.9%, 33.7%, and 40.9% correspondingly.

GAM4water: An R-based method for extracting wetted areas from remotely-sensed images

We present ‘GAM4water,’ a R-based method to classify wetted and non-wetted (dry) areas using remotely sensed image indices derived from such images. The GAM4water classification algorithm is built around a Generalized Additive Model (GAM) capable of accounting for non-linear responses. GAM4water can use any type of radiometric data, whether from drones, satellites or other platforms, and can be used with data of different spatial resolutions, geographic extents and spatial reference systems. It is a supervised tool that uses pixel information to distinguish between wetted and dry areas within an image set, extract them and produce a rich output that includes a binary raster, polygons of wetted areas, and a classification performance report. We tested the method in two case-studies, one using high resolution drone images and another using satellite images. The tests show that GAM4water can produce highly accurate classifications of wetted and non-wetted areas, and has the additional benefit of being easily customizable and not requiring complex implementation procedures.•This paper introduces the first R based method of wetted area extraction for remotely-sensed images.•The method is based on Generalized Additive Models and is applicable to any remotely-sensed data.

Constructing a measurement-based spatially explicit inventory of US oil and gas methane emissions (2021)

Abstract. Accurate and comprehensive quantification of oil and gas methane emissions is pivotal in informing effective methane mitigation policies while also supporting the assessment and tracking of progress towards emissions reduction targets set by governments and industry. While national bottom-up source-level inventories are useful for understanding the sources of methane emissions, they are often unrepresentative across spatial scales, and their reliance on generic emission factors produces underestimations when compared with measurement-based inventories. Here, we compile and analyze previously reported ground-based facility-level methane emissions measurements (n=1540) in the major US oil- and gas-producing basins and develop representative methane emission profiles for key facility categories in the US oil and gas supply chain, including well sites, natural-gas compressor stations, processing plants, crude-oil refineries, and pipelines. We then integrate these emissions data with comprehensive spatial data on national oil and gas activity to estimate each facility's mean total methane emissions and uncertainties for the year 2021, from which we develop a mean estimate of annual national methane emissions resolved at 0.1° × 0.1° spatial scales (∼ 10 km × 10 km). From this measurement-based methane emissions inventory (EI-ME), we estimate total US national oil and gas methane emissions of approximately 16 Tg (95 % confidence interval of 14–18 Tg) in 2021, which is ∼ 2 times greater than the EPA Greenhouse Gas Inventory. Our estimate represents a mean gas-production-normalized methane loss rate of 2.6 %, consistent with recent satellite-based estimates. We find significant variability in both the magnitude and spatial distribution of basin-level methane emissions, ranging from production-normalized methane loss rates of < 1 % in the gas-dominant Appalachian and Haynesville regions to > 3 %–6 % in oil-dominant basins, including the Permian, Bakken, and the Uinta. Additionally, we present and compare novel comprehensive wide-area airborne remote-sensing data and results for total area methane emissions and the relative contributions of diffuse and concentrated methane point sources as quantified using MethaneAIR in 2021. The MethaneAIR assessment showed reasonable agreement with independent regional methane quantification results in sub-regions of the Permian and Uinta basins and indicated that diffuse area sources accounted for the majority of the total oil and gas emissions in these two regions. Our assessment offers key insights into plausible underlying drivers of basin-to-basin variabilities in oil and gas methane emissions, emphasizing the importance of integrating measurement-based data when developing high-resolution spatially explicit methane inventories in support of accurate methane assessment, attribution, and mitigation. The high-resolution spatially explicit EI-ME inventory is publicly available at https://doi.org/10.5281/zenodo.10734299 (Omara, 2024).

Self-Attention Multiresolution Analysis-Based Informal Settlement Identification Using Remote Sensing Data

The global dilemma of informal settlements persists alongside the fast process of urbanization. Various methods for analyzing remotely sensed images to identify informal settlements using semantic segmentation have been extensively researched, resulting in the development of numerous supervised and unsupervised algorithms. Texture-based analysis is a topic extensively studied in the literature. However, it is important to note that approaches that do not utilize a multiresolution strategy are unable to take advantage of the fact that texture exists at different spatial scales. The capacity to do online mapping and precise segmentation on a vast scale while considering the diverse characteristics present in remotely sensed images carries significant consequences. This research presents a novel approach for identifying informal settlements using multiresolution analysis and self-attention techniques. The technique shows potential for being resilient in the presence of inherent variability in remotely sensed images due to its capacity to extract characteristics at many scales and prioritize areas that contain significant information. Segmented pictures underwent an accuracy assessment, where a comparison analysis was conducted based on metrics such as mean intersection over union, precision, recall, F-score, and overall accuracy. The proposed method’s robustness is demonstrated by comparing it to various state-of-the-art techniques. This comparison is conducted using remotely sensed images that have different spatial resolutions and informal settlement characteristics. The proposed method achieves a higher accuracy of approximately 95%, even when dealing with significantly different image characteristics.

Spatial and Temporal Changes in Habitat Quality and Driving Forces in Typical Loess Hill and Gully Areas：A Case Study of the Zuli River Basin

Loess hills and gully areas are one of the important ecological barriers in China, and the study of the spatial and temporal changes of its habitat quality and its driving force is of great significance to guaranteeing the ecological security of China and safeguarding the national ecological rights and interests. Taking the Zuli River Basin as an example, the spatiotemporal distribution of the remote-sensing ecological index （RSEI） from 2000 to 2020 was systematically investigated using the Google Earth Engine platform and Landsat remote-sensing data. Combined with the coefficient of variation CV, the Theil-Sen Median slope estimation, the Mann-Kendall test of significance, and the Hurst index, the spatial and temporal changes of habitat quality in the study area were analyzed over a period of 20 years, and the effects of six major driving factors on the spatial distribution of RSEI were investigated using the geodetector method. The results of the study showed that： ① From 2000 to 2020, the value of the RSEI showed a downward and then upward trend, with an average annual increase of 0.084 5·（10 a）-1. ② During the 20-year period, the habitat quality improvement area accounted for 92.06%, of which the significant improvement area accounted for 28.49%, and the improvement area was mainly in Huining County, whereas the habitat degradation area only accounted for 7.82%. The trend of future ecological conditions showed that 74.98% of the areas would show a trend of continuous improvement or future improvement, but there would still be a potential risk of ecological degradation in 23.48% of the areas in the future. ③ Climate factors such as precipitation were the key factors affecting the habitat quality in the Zu Li River Basin； the interaction between factors had a higher explanatory power than that of any single factor on the habitat quality, among which the interaction between the precipitation factor and the elevation factor had the strongest explanatory power. The interaction between the terracing factor and the environmental factor significantly increased the explanatory power of the spatial variance, which indicated that terracing played an important role in improving habitat quality. The results of this study can provide a scientific basis for the management and sustainable development of the ecological environment in the loess hills and gullies.

L-Band Synthetic Aperture Radar and Its Application for Forest Parameter Estimation, 1972 to 2024: A Review.

Optical remote sensing can effectively capture 2-dimensional (2D) forest information, such as woodland area and percentage forest cover. However, accurately estimating forest vertical-structure relevant parameters such as height using optical images remains challenging, which leads to low accuracy of estimating forest stocks like biomass and carbon stocks. Thus, accurately obtaining vertical structure information of forests has become a significant bottleneck in the application of optical remote sensing to forestry. Microwave remote sensing such as synthetic aperture radar (SAR) and polarimetric SAR provides the capability to penetrate forest canopies with the L-band signal, and is particularly adept at capturing the vertical structure information of forests, which is an alternative ideal remote-sensing data source to overcome the aforementioned limitation. This paper utilizes the Citexs data analysis platform, along with the CNKI and PubMed databases, to investigate the advancements of applying L-band SAR technology to forest canopy penetration and structure-parameter estimation, and provides a comprehensive review based on 58 relevant articles from 1978 to 2024 in the PubMed database. The metrics, including annual publication numbers, countries/regions from which the publications come, institutions, and first authors, with the visualization of results, were utilized to identify development trends. The paper summarizes the state of the art and effectiveness of L-band SAR in addressing the estimation of forest height, moisture, and forest stocks, and also examines the penetration depth of the L-band in forests and highlights key influencing factors. This review identifies existing limitations and suggests research directions in the future and the potential of using L-band SAR technology for forest parameter estimation.

Remote and Proximal Sensors Data Fusion: Digital Twins in Irrigation Management Zoning.

The scientific field of precision agriculture employs increasingly innovative techniques to optimize inputs, maximize profitability, and reduce environmental impact. However, obtaining a high number of soil samples is challenging in order to make precision agriculture viable. There is a trade-off between the amount of data needed and the time and resources spent to obtain these data compared to the accuracy of the maps produced with more or fewer points. In the present study, the research was based on an exhaustive dataset of apparent electrical conductivity (aEC) containing 3906 points distributed along 26 transects with spacing between each of up to 40 m, measured by the proximal soil sensor EM38-MK2, for a grain-producing area of 72 ha in São Paulo, Brazil. A second sparse dataset was simulated, showing only four transects with a 400 m distance and, in the end, only 162 aEC points. The aEC map via ordinary kriging (OK) from the grid with 26 transects was considered the reference, and two other mapping approaches were used to map aEC via sparse grid: kriging with external drift (KED) and geographically weighted regression (GWR). These last two methods allow the increment of auxiliary variables, such as those obtained by remote sensors that present spatial resolution compatible with the pivot scale, such as data from the Landsat-8, Aster, and Sentinel-2 satellites, as well as ten terrain covariates derived from the Alos Palsar digital elevation model. The KED method, when used with the sparse dataset, showed a relatively good fit to the aEC data (R2 = 0.78), with moderate prediction accuracy (MAE = 1.26, RMSE = 1.62) and reasonable predictability (RPD = 1.76), outperforming the GWR method, which had the weakest performance (R2 = 0.57, MAE = 1.78, RMSE = 2.30, RPD = 0.81). The reference aEC map using the exhaustive dataset and OK showed the highest accuracy with an R2 of 0.97, no systematic bias (ME = 0), and excellent precision (RMSE = 0.56, RPD = 5.86). Management zones (MZs) derived from these maps were validated using soil texture data from clay samples measured at 0-10 cm depth in a grid of 72 points. The KED method demonstrated the highest potential for accurately defining MZs for irrigation, producing a map that closely resembled the reference MZ map, thereby providing reliable guidance for irrigation management.

Assessment of Post-Harvest Rice Crop Biomass and Carbon Stock using Remote Sensing Data in Google Earth Engine

Assessment of Post-Harvest Rice Crop Biomass and Carbon Stock using Remote Sensing Data in Google Earth Engine

Мониторинг развития Дуплетного объекта взрыва газа С22 на полуострове Ямал по данным дистанционного зондирования Земли

The paper presents a comprehensive study of the C22 gas blowout Doublet object formed in 2023 in the central part of Yamal peninsula carried out with the use of remote sensing (RS) data and unmanned aerial vehicle (UAV). The object is situated 12.7 km south of the Bovanenkovo field. The uniqueness of the C22 crater lies in its location — 230 m from a similar, widely-known C2 object exploded in 2012, which is why the C22 object is named ‘Doublet’. Based on RS data the researchers have determined that within August 23 and September 3, 2023 the C22 permafrost heaving mound (PHM) exploded. According to ArcticDEM data for the period 2011-2023, the features of changes in the size of C22 PHM have been studied, including an abnormally high average growth rate of 44 cm/year three years before its explosion, which can serve as one of the criteria for identifying explosive PHM objects. The UAV data of May 14, 2024 has resulted in building a 3D model, which displays a partially snow-covered cavity in a ground ice massif. The depth of the cavity from the crater parapet is at least 28.5 m, the diameter of the crater neck is about 13 m. In the lower part, the cavity widens to 26 m and additionally extends by at least 8 m in the NNW direction at an azimuth of about 341°, which is consistent with the direction of the faults of the Bovanenkovo field identified by seismic exploration data. The bottom of the cavity has an elliptical shape with the size from 26×33 m to 26×41 m. The study is interdisciplinary and is included in the list of critical technologies for the prevention and reduction of risks of natural and man-made emergencies.

Modelling landscape-scale occurrences of common grassland species in a topographically complex mountainous environment

Mountainous regions typically harbour high plant diversity but are also characterised by low sampling intensity. Coarse-scale species distribution models can provide insights into the distribution of poorly sampled species, but the required bioclimatic data are often limited in these landscapes. In comparison, several environmental factors that vary over relatively fine scales in mountain environments (e.g. measures of topography) can be quantified from remotely-sensed data, and can potentially provide direct and indirect measures of biologically-relevant habitat characteristics in mountains. Therefore, in this study, we combine field-sampled floristic data with environmental predictors derived from remotely-sensed data, to model the ecological niches of 19 montane plant species in the Maloti-Drakensberg mountains, South Africa. The resulting models varied considerably in their performance, and species showed generally inconsistent responses to environmental predictors, with altitude and distance to watershed being most frequently included in models. These results highlight the species-specificity of the forb species’ environmental tolerances and requirements, suggesting that environmental change may result in re-shuffling of community composition, instead of intact communities shifting along gradients. Furthermore, while the relatively high importance of altitude (a proxy for temperature) and topographic wetness index (a proxy for soil moisture) suggest that the flora of this region will be sensitive to shifts in temperature and rainfall patterns, several non-climatic environmental variables were also influential. Our findings indicate that local response to climate change in mountains might be especially constrained by soil type and topographic variables, supporting the important influence of non-climatic factors in microclimatic refugia dynamics.

Improved Winter Wheat Yield Estimation by Combining Remote Sensing Data, Machine Learning, and Phenological Metrics

Accurate yield prediction is essential for global food security and effective agricultural management. Traditional empirical statistical models and crop models face significant limitations, including high computational demands and dependency on high-resolution soil and daily weather data, that restrict their scalability across different temporal and spatial scales. Moreover, the lack of sufficient observational data further hinders the broad application of these methods. In this study, building on the SCYM method, we propose an integrated framework that combines crop models and machine learning techniques to optimize crop yield modeling methods and the selection of vegetation indices. We evaluated three commonly used vegetation indices and three widely applied ML techniques. Additionally, we assessed the impact of combining meteorological and phenological variables on yield estimation accuracy. The results indicated that the green chlorophyll vegetation index (GCVI) outperformed the normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI) in linear models, achieving an R2 of 0.31 and an RMSE of 396 kg/ha. Non-linear ML methods, particularly LightGBM, demonstrated superior performance, with an R2 of 0.42 and RMSE of 365 kg/ha for GCVI. The combination of GCVI with meteorological and phenological data provided the best results, with an R2 of 0.60 and an RMSE of 295 kg/ha. Our proposed framework significantly enhances the accuracy and efficiency of winter wheat yield estimation, supporting more effective agricultural management and policymaking.

Monitoring Soybean Soil Moisture Content Based on UAV Multispectral and Thermal-Infrared Remote-Sensing Information Fusion.

By integrating the thermal characteristics from thermal-infrared remote sensing with the physiological and structural information of vegetation revealed by multispectral remote sensing, a more comprehensive assessment of the crop soil-moisture-status response can be achieved. In this study, multispectral and thermal-infrared remote-sensing data, along with soil-moisture-content (SMC) samples (0~20 cm, 20~40 cm, and 40~60 cm soil layers), were collected during the flowering stage of soybean. Data sources included vegetation indices, texture features, texture indices, and thermal-infrared vegetation indices. Spectral parameters with a significant correlation level (p < 0.01) were selected and input into the model as single- and fuse-input variables. Three machine learning methods, eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Genetic Algorithm-optimized Backpropagation Neural Network (GA-BP), were utilized to construct prediction models for soybean SMC based on the fusion of UAV multispectral and thermal-infrared remote-sensing information. The results indicated that among the single-input variables, the vegetation indices (VIs) derived from multispectral sensors had the optimal accuracy for monitoring SMC in different soil layers under soybean cultivation. The prediction accuracy was the lowest when using single-texture information, while the combination of texture feature values into new texture indices significantly improved the performance of estimating SMC. The fusion of vegetation indices (VIs), texture indices (TIs), and thermal-infrared vegetation indices (TVIs) provided a better prediction of soybean SMC. The optimal prediction model for SMC in different soil layers under soybean cultivation was constructed based on the input combination of VIs + TIs + TVIs, and XGBoost was identified as the preferred method for soybean SMC monitoring and modeling, with its R2 = 0.780, RMSE = 0.437%, and MRE = 1.667% in predicting 0~20 cm SMC. In summary, the fusion of UAV multispectral and thermal-infrared remote-sensing information has good application value in predicting SMC in different soil layers under soybean cultivation. This study can provide technical support for precise management of soybean soil moisture status using the UAV platform.

Identification of Pasture Degradation Using Remote Sensing Data and Machine Learning: A Case Study of Obichnik

The degradation of pastures and meadows is a global problem with a wide range of impacts. It affects farmers in different ways, such as decreases in cattle production, milk yield, and forage quality. Still, it also has other side effects, such as loss of biodiversity, loss of resources, etc. In this study, the degradation of a semi-natural pasture near the village of Obichnik, Bulgaria, was evaluated using machine learning algorithms, and an unmanned aerial vehicle (UAV) obtained visual spectrum images. A high-quality (HQ) orthomosaic of the area was created and numerous regions of interest were manually marked for training and validation purposes. Three machine learning algorithms were used—Maximum likelihood, Random trees (RT), and Support Vector Machine (SVM). Furthermore, object-based and pixel-based approaches were utilized. The obtained results indicate that the object-based RT and SVM models provide significantly better accuracy, with their Cohen’s Kappa reaching 0.86 and 0.82, respectively. The performed classification showed that approximately 61% of the investigated pasture area is covered with grass, which indicates light-to-medium degradation.

Remote Sensing Data Assimilation in Crop Growth Modeling from an Agricultural Perspective: New Insights on Challenges and Prospects

The frequent occurrence of global climate change and natural disasters highlights the importance of precision agricultural monitoring, yield forecasting, and early warning systems. The data assimilation method provides a new possibility to solve the problems of low accuracy of yield prediction, strong dependence on the field, and poor adaptability of the model in traditional agricultural applications. Therefore, this study makes a systematic literature retrieval based on Web of Science, Scopus, Google Scholar, and PubMed databases, introduces in detail the assimilation strategies based on many new remote sensing data sources, such as satellite constellation, UAV, ground observation stations, and mobile platforms, and compares and analyzes the progress of assimilation models such as compulsion method, model parameter method, state update method, and Bayesian paradigm method. The results show that: (1) the new remote sensing platform data assimilation shows significant advantages in precision agriculture, especially in emerging satellite constellation remote sensing and UAV data assimilation. (2) SWAP model is the most widely used in simulating crop growth, while Aquacrop, WOFOST, and APSIM models have great potential for application. (3) Sequential assimilation strategy is the most widely used algorithm in the field of agricultural data assimilation, especially the ensemble Kalman filter algorithm, and hierarchical Bayesian assimilation strategy is considered to be a promising method. (4) Leaf area index (LAI) is considered to be the most preferred assimilation variable, and the study of soil moisture (SM) and vegetation index (VIs) has also been strengthened. In addition, the quality, resolution, and applicability of assimilation data sources are the key bottlenecks that affect the application of data assimilation in the development of precision agriculture. In the future, the development of data assimilation models tends to be more refined, diversified, and integrated. To sum up, this study can provide a comprehensive reference for agricultural monitoring, yield prediction, and crop early warning by using the data assimilation model.

Using USLE, GIS and remote sensing for the soil loss assessment in the National Park of Theniet El Had, Algeria

Soil water erosion is one of the problems that affect the environment, agriculture and social life by threatening several land surfaces. The objective of this study is to use the USLE model, GIS and remote sensing (RS) to estimate the annual rate of soil loss by water erosion in the Theniet El Had National Park (THNP) which belongs to the mountainous ecosystem of Djebel El Meddad, located in the northwest of Algeria. The use of the USLE model takes into account the five factors controlling water erosion, namely: the rain erosivity (R) determined from the annual rainfall data, the soil erodibility (K) developed from soil survey data, the slope lengths (LS) generated by using DEM, the vegetation cover (C) by the use of RS data and erosion control management practices (P) by field trips. The integration of these factors made it possible to establish the quantitative map of the annual rate of soil loss varying between 0.02 and 55.10 (t/ha.year), with an average of around 6.64 (t/ha.year). Five erosion aggressiveness classes are used; very weak, weak, moderate, strong and very strong which represent a rate respectively of 23.70, 44.65, 22.72, 4.41 and 4.52 % of the study area surface. The areas with high and very high erosion rates are located in the north having a very rugged relief and low vegetation cover. This study can be used in the mountainous ecosystems and it will make it possible to set up priority intervention zones to combat the risk of water erosion.