Integration Of Satellite Data Research Articles

Detailed analysis of air pollution in the Canadian prairie region: A step toward net-zero emission.

Industrial, agricultural, and natural pollution pose a critical problem for the Prairie provinces of Canada, with significant environmental and health concerns. This study addresses a critical knowledge gap by assessing the cumulative impacts of pollutants in the Prairie region, which hosts 40% of the Canada's indigenous population, often living near these pollution sources. By innovatively integrating Sentinel-5P satellite data, Google Earth Engine, ArcGIS, and Python, we show the trends in CO, NO₂, HCHO, SO₂, and aerosols from 2019 to 2023 at high resolution for the entire region, which sheds new light on the dynamics that operate beyond conventional air quality monitoring. Key findings are summer peaks for NO₂ and aerosols in southern Saskatchewan, related to agriculture, while winter peaks for CO and SO₂ in Alberta and Saskatchewan signal the need for renewable heating options. Alberta had the highest levels for most of the pollutants; however, CO concentrations were the highest in Manitoba. By integrating satellite data with ground-based measures, we also offer a more comprehensive and accurate analysis to pinpoint regional pollution issues, to help toward development of data-driven air quality strategies, and to enhance alignment of federal-provincial initiatives. These insights promote targeted interventions lowering exposure risk while encouraging practical sustainability in the Prairie region, and aid Canada in achieving its net-zero emission goal.

Monitoring Coastal Water Turbidity Using Sentinel2—A Case Study in Los Angeles

Los Angeles coastal waters are an ecologically important marine habitat and a famed recreational area for tourists. Constant surveillance is essential to ensure compliance with established health standards and to address the persistent water quality challenges in the region. Remotely sensed datasets are increasingly being applied toward improved detection of water quality by augmenting monitoring programs with spatially intensive and accessible data. This study evaluates the potential of satellite remote sensing to augment traditional monitoring by analyzing the relationship between in situ and satellite-derived turbidity data. Field measurements were performed from July 2021 to March 2024 to build synchronous matchup datasets consisting of satellite and field data. Correlation analysis indicated a positive relationship between satellite-derived and field-measured turbidity (R2 = 0.451). Machine learning models were assessed for predictive accuracy, with the random forest model achieving the highest performance (R2 = 0.632), indicating its robustness in modeling complex turbidity patterns. Seasonal trends revealed higher turbidity during wet months, likely due to stormwater runoff from the Ballona Creek watershed. Despite limitations from cloud cover and spatial resolution, the findings suggest that integrating satellite data with machine learning can enhance large-scale, efficient turbidity monitoring in coastal waters.

Assessment of Artificial Light at Night Across Geographical Features in the Sicilian Coastal Zone

This study investigates the impact of artificial light at night (ALAN) along the Sicilian coasts, using satellite data from 2016 to 2023, focusing on three distinct spatial domains: terrestrial areas within 1 km from the coastline, marine areas extending up to 1 km offshore, and marine areas up to 1 nautical mile from the coast. In coastal zones, ALAN is a significant anthropogenic pressure with potentially detrimental effects on ecosystems. By integrating satellite data with geographic datasets such as Corine Land Cover (CLC), Natura 2000 protected areas, and Posidonia oceanica meadows, this study aims to characterize and analyse the temporal and spatial variations in ALAN across these domains. The findings reveal substantial differences in light pollution between domains and over time, with coastal terrestrial areas exhibiting the highest levels of ALAN. In contrast, marine areas further offshore experience reduced light pollution, particularly within the 1-nautical-mile domain. This study also indicates that protected areas, especially those within the Natura 2000 network, show significantly lower ALAN levels than non-protected areas, highlighting the effectiveness of conservation efforts. Statistical analyses, including ANOVAs, demonstrate that factors such as geographic domain, year, province, and CLC classes significantly influence ALAN distribution. This study advocates for considering ALAN as a critical factor in environmental impact assessments, such as those under the Maritime Spatial Planning Directive (MSP) and Marine Strategy Framework Directive (MSFD), providing valuable insights to support policies aimed at mitigating the environmental impact of light pollution on coastal and marine ecosystems.

Mapping Methane—The Impact of Dairy Farm Practices on Emissions Through Satellite Data and Machine Learning

Methane emissions from dairy farms are a significant driver of climate change, yet their relationship with farm-specific practices remains poorly understood. This study employs Sentinel-5P satellite-derived methane column concentrations as a proxy to examine emission dynamics across 11 dairy farms in Eastern Canada, using data collected between January 2020 and December 2022. By integrating advanced analytics, we identified key drivers of methane concentrations, including herd genetics, feeding practices, and management strategies. Statistical tools such as Variance Inflation Factor (VIF) and Principal Component Analysis (PCA) addressed multicollinearity, stabilizing predictive models. Machine learning approaches—Random Forest and Neural Networks—revealed a strong negative correlation between methane concentrations and the Estimated Breeding Value (EBV) for protein percentage, demonstrating the potential of genetic selection for emissions mitigation. Our approach refined concentration estimates by integrating satellite data with localized atmospheric modeling, enhancing accuracy and spatial resolution. These findings highlight the transformative potential of combining satellite observations, machine learning, and farm-level characteristics to advance sustainable dairy farming. This research underscores the importance of targeted breeding programs and management strategies to optimize environmental and economic outcomes. Future work should expand datasets and apply inversion modeling for finer-scale emission quantification, advancing scalable solutions that balance productivity with ecological sustainability.

Improving Flood Streamflow Estimation of Ungauged Small Reservoir Basins Using Remote Sensing and Hydrological Modeling

Small- and medium-sized reservoirs significantly alter natural flood processes, making it essential to understand their impact on runoff for effective water resource management. However, the lack of measured data for most small reservoirs poses challenges for accurately simulating their behavior. This study proposes a novel method that utilizes readily available satellite observation data, integrating hydraulic, hydrological, and mathematical formulas to derive outflow coefficients. Based on the Grid-XinAnJiang (GXAJ) model, the enhanced GXAJ-R model accounts for the storage and release effects of ungauged reservoirs and is applied to the Tunxi watershed. Results show that the original GXAJ model achieved a stable performance with an average NSE of 0.88 during calibration, while the NSE values of the GXAJ and GXAJ-R models during validation ranged from 0.78 to 0.97 and 0.85 to 0.99, respectively, with an average improvement of 0.03 in the GXAJ-R model. This enhanced model significantly improves peak flow simulation accuracy, reduces relative flood peak error by approximately 10%, and replicates the flood flow process with higher fidelity. Additionally, the area–volume model derived from classified small-scale data demonstrates high accuracy and reliability, with correlation coefficients above 0.8, making it applicable to other ungauged reservoirs. The OTSU-NDWI method, which improves the NDWI, effectively enhances the accuracy of water body extraction from remote sensing, achieving overall accuracy and kappa coefficient values exceeding 0.8 and 0.6, respectively. This study highlights the potential of integrating satellite data with hydrological models to enhance the understanding of reservoir behavior in data-scarce regions. It also suggests the possibility of broader applications in similarly ungauged basins, providing valuable tools for flood management and risk assessment.

Integrating Copernicus LMS with ground measurements data for leaf area index and biomass assessment for grasslands in Poland and Norway

ABSTRACT The integration of satellite data from the Copernicus Land Monitoring Service (CLMS) with ground-based measurements represents a pioneering approach to the assessment of leaf area index (LAI) and in situ biomass at grasslands in Poland and Norway. The aim of this study was to develop a method for assessing grass growth conditions and predicting biomass yield based on Sentinel-2 data and CLMS products. LAI values derived from CLMS were compared with in-situ measurements on grassland plots in the two regions of Podlaskie (PL84) and Wielkopolskie (PL41). Small random statistical errors observed in the differences represent a significant opportunity to use Copernicus data to develop a relationship model for biomass prediction. The NDII index calculated using Sentinel2 was considered important for biomass assessment in the humid areas of Norway. This relational biomass prediction model could provide valuable information to farmers, improving their ability to manage grasslands effectively. As a result of the research, relational models were developed has been developed to predict grassland fresh biomass yield with an R 2 accuracy of 0.72 for the first cut, 0.81 for the second cut and 0.91 for the third cut. This allows farmers to effectively manage and monitor grassland throughout the growing season.

Multi-temporal image analysis of wetland dynamics using machine learning algorithms

Wetlands play a crucial role in enhancing groundwater quality, mitigating natural hazards, controlling erosion, and providing essential habitats for unique flora and wildlife. Despite their significance, wetlands are facing decline in various global locations, underscoring the need for effective mapping, monitoring, and predictive modeling approaches. Recent advances in machine learning, time series earth observation data, and cloud computing have opened up new possibilities to address the challenges of large-scale wetlands mapping and dynamics forecasting. This research conducts a comprehensive analysis of wetland dynamics in the Thatta region, encompassing Haleji & Kinjhar Lake in Pakistan, and evaluates the efficacy of different classification systems. Leveraging Google Earth Engine, Landsat imagery, and various spectral indices, we assess four classification techniques to derive accurate wetland mapping results. Our findings demonstrate that Random Forest emerged as the most efficient and accurate method, achieving 87% accuracy across all time periods. Change detection analysis reveals a significant and alarming decline in Haleji & Kinjhar Lake wetlands over 1990–2020, primarily driven by agricultural expansion, urbanization, groundwater extraction, and climate change impacts like rising temperatures and reduced precipitation. If left unaddressed, this continued wetland loss could have severe implications for aquatic and terrestrial species, water and soil quality, wildlife populations, and local livelihoods. The study predicts future wetland dynamics under different scenarios - enhancing drainage for farmland conversion (10–20% increase), increasing urbanization (10–20% expansion), escalating groundwater extraction (7.2m annual decline), and climate change (up to 5 °C warming and 54% precipitation deficit by 2050). These scenarios forecast sustained long-term wetland deterioration driven by anthropogenic pressures and climate change. To guide conservation strategies, the research integrates satellite data analytics, machine learning algorithms, and spatial modeling to generate actionable insights into multifaceted wetland vulnerabilities. Findings provide a robust baseline to inform policies ensuring sustainable management and preservation of these vital ecosystems amidst escalating human and climate threats. Over 1990–2020, the Thatta region witnessed a 352.8 sq.km loss of wetlands, necessitating urgent restoration efforts to safeguard their invaluable ecosystem services.

Machine learning reveals biological activities as the dominant factor in controlling deoxygenation in the South Yellow Sea

Dissolved oxygen (DO) is a crucial element for both biotic and abiotic processes in marine ecosystems, but has declined globally in recent decades. Therefore, there is an urgent need for solid large-scale and continuous estimation of DO concentration in vital ecosystems, such as coastal areas. A random forest (RF) model for DO in South Yellow Sea (SYS) was developed by integrating satellite data and simulation data during 2011–2019. The root mean squared error (RMSE) for the training and test sets were 0.514 mg/L and 0.732 mg/L, respectively. Spatiotemporal distributions of DO of multiple layers in the study area during 2011–2019 were very well reproduced by the RF model and showed a slight decline trend in most SYS areas, while more intense decline occurred in the deep central SYS. The analysis of the mechanisms of DO decline in the South Yellow Sea cold water mass (SYSCWM), located in the deep central SYS, indicates that the deoxygenation here is largely due to biological activities. This finding may have implications for studies on drivers of deoxygenation in coastal areas. Furthermore, integrating satellite data with machine learning models can offer a powerful approach to capturing the continuous spatiotemporal characteristics of ocean parameters over large spatial scales.

Enhancing Forest Canopy Height Mapping in Kaziranga National Park, Assam, by Integrating LISS IV and SAR data with GEDI LiDAR data Using Machine Learning

Abstract. This study investigates the integration of spaceborne Global Ecosystem Dynamics Investigation (GEDI) LiDAR data with optical imagery from Linear Imaging Self Scanning Sensor (LISS IV), Sentinel-1 Synthetic Aperture Radar (SAR) and PALSAR data for continuous forest canopy height mapping in Kaziranga National Park (KNP), Assam for the years 2018 and 2022. Four machine learning models were trained and evaluated to assess the predictive ability of LISS IV data in conjunction with SAR variables. The mean canopy height was measured at approximately 8.58 m in 2018, which increased to about 9.07m in 2022. Results reveal Extreme Gradient Boosting (XGB) as the top-performing model, achieving an RMSE of 5.47m and an R2 of 0.55. In comparison, Random Forest (RF), Support Vector Machine (SVM), and k-Nearest Neighbors (kNN) achieved RMSE values of 5.49, 5.51, and 5.73, respectively. Analysis shows a prevalent occurrence of canopy heights below 5 meters in KNP (more than 35% of the area), while taller canopies beyond 20m can be found in less than 5% of the area. This finding underscores the importance of integrating satellite data and machine learning and highlights the novel application of LISS IV data in enhancing canopy height mapping. Furthermore, it represents the first comprehensive attempt to map canopy height in KNP, laying the groundwork for further research on biomass assessment and carbon sequestration in this vital biodiversity hotspot. Overall, the study highlights the potential of leveraging advanced remote sensing technologies and machine learning approaches for improved understanding and management of forest ecosystems.

Enhancing the Precision of Forest Growing Stock Volume in the Estonian National Forest Inventory with Different Predictive Techniques and Remote Sensing Data

Estimating forest growing stock volume (GSV) is crucial for forest growth and resource management, as it reflects forest productivity. National measurements are laborious and costly; however, integrating satellite data such as optical, Synthetic Aperture Radar (SAR), and airborne laser scanning (ALS) with National Forest Inventory (NFI) data and machine learning (ML) methods has transformed forest management. In this study, random forest (RF), support vector regression (SVR), and Extreme Gradient Boosting (XGBoost) were used to predict GSV using Estonian NFI data, Sentinel-2 imagery, and ALS point cloud data. Four variable combinations were tested: CO1 (vegetation indices and LiDAR), CO2 (vegetation indices and individual band reflectance), CO3 (LiDAR and individual band reflectance), and CO4 (a combination of vegetation indices, individual band reflectance, and LiDAR). Across Estonia’s geographical regions, RF consistently delivered the best performance. In the northwest (NW), the RF model achieved the best performance with the CO3 combination, having an R2 of 0.63 and an RMSE of 125.39 m3/plot. In the southwest (SW), the RF model also performed exceptionally well, achieving an R2 of 0.73 and an RMSE of 128.86 m3/plot with the CO4 variable combination. In the northeast (NE), the RF model outperformed other ML models, achieving an R2 of 0.64 and an RMSE of 133.77 m3/plot under the CO4 combination. Finally, in the southeast (SE) region, the best performance was achieved with the CO4 combination, yielding an R2 of 0.70 and an RMSE of 21,120.72 m3/plot. These results underscore RF’s precision in predicting GSV across diverse environments, though refining variable selection and improving tree species data could further enhance accuracy.

Habitat quality outweighs the human footprint in driving spatial patterns of Cetartiodactyla in the Kunlun-Pamir Plateau

The Human Footprint (HFP) and Habitat Quality (HQ) are critical factors influencing the species' distribution, yet their relation to biodiversity, particularly in mountainous regions, still remains inadequately understood. This study aims to identify the primary factor that affects the biodiversity by comparing the impact of the HFP and HQ on the species’ richness of Cetartiodactyla in the Kunlun-Pamir Plateau and four protected areas: The Pamir Plateau Wetland Nature Reserve, Taxkorgan Wildlife Nature Reserve, Middle Kunlun Nature Reserve and Arjinshan Nature Reserve through multi-source satellite remote sensing product data. By integrating satellite data with the Integrated Valuation of Ecosystem Services and Trade-offs (InVEST)HQ model and utilizing residual and linear regression analysis, we found that: (1) The Wildness Area (WA) predominantly underwent a transition to a Highly Modified Area (HMA) and Intact Area (IA), with a notable 12.02% rise in stable regions, while 58.51% rather experienced a negligible decrease. (2) From 1985 to 2020, the Kunlun-Pamir Plateau has seen increases in the forestland, water, cropland and shrubland, alongside declines in bare land and grassland, denoting considerable land cover changes. (3) The HQ degradation was significant, with 79.81% of the area showing degradation compared to a 10.65% improvement, varying across the nature reserves. (4) The species richness of Cetartiodactyla was better explained by HQ than by HFP on the Kunlun-Pamir Plateau (52.99% vs. 47.01%), as well as in the Arjinshan Nature Reserve (81.57%) and Middle Kunlun Nature Reserve (56.41%). In contrast, HFP was more explanatory in the Pamir Plateau Wetland Nature Reserve (88.89%) and the Taxkorgan Wildlife Nature Reserve (54.55%). Prioritizing the restoration of degraded habitats areas of the Kunlun Pamir Plateau could enhance Cetartiodactyla species richness. These findings provide valuable insights for the biodiversity management and conservation strategies in the mountainous regions.

Annotated Dataset for Training Cloud Segmentation Neural Networks Using High-Resolution Satellite Remote Sensing Imagery

The integration of satellite data with deep learning has revolutionized various tasks in remote sensing, including classification, object detection, and semantic segmentation. Cloud segmentation in high-resolution satellite imagery is a critical application within this domain, yet progress in developing advanced algorithms for this task has been hindered by the scarcity of specialized datasets and annotation tools. This study addresses this challenge by introducing CloudLabel, a semi-automatic annotation technique leveraging region growing and morphological algorithms including flood fill, connected components, and guided filter. CloudLabel v1.0 streamlines the annotation process for high-resolution satellite images, thereby addressing the limitations of existing annotation platforms which are not specifically adapted to cloud segmentation, and enabling the efficient creation of high-quality cloud segmentation datasets. Notably, we have curated the Annotated Dataset for Training Cloud Segmentation (ADTCS) comprising 32,065 images (512 × 512) for cloud segmentation based on CloudLabel. The ADTCS dataset facilitates algorithmic advancement in cloud segmentation, characterized by uniform cloud coverage distribution and high image entropy (mainly 5–7). These features enable deep learning models to capture comprehensive cloud characteristics, enhancing recognition accuracy and reducing ground object misclassification. This contribution significantly advances remote sensing applications and cloud segmentation algorithms.

AN AUTOMATED CROP MONITORING AND IRRIGATION SYSTEM WITH PREDICTIVE ANALYSIS

Background: The rising global population and decreasing agricultural land challenge the food supply, worsened by land degradation and water scarcity. Using IoT solutions, precision farming offers promise for addressing these issues by enhancing productivity, profitability, and environmental sustainability. The paper proposes an IoT-based automated monitoring and irrigation system with predictive analysis as a solution. Aims: To develop an IoT-based irrigation model with cloud computing, a mobile app for remote monitoring and irrigation control, and a predictive analysis method for forecasting weather conditions. Methods: IoT sensors are connected to a node MCU, and they monitor real-time temperature, humidity, and soil moisture. A water pump adjusts irrigation accordingly. Data is sent to ThingSpeak for visualization and Firebase for storage and is accessible via a mobile app. Predictive analysis combines sensor and historical weather data using the Random Forest algorithm to optimize irrigation. This determines the ideal irrigation frequency, duration, and timing based on predicted temperature and soil moisture levels, ensuring optimal soil moisture for plant growth. Results: The system exhibited encouraging outcomes. It displayed transformative potential by harnessing IoT, cloud computing, and predictive analytics. Offering precise soil moisture monitoring, instant data access, and tailored advice, the system can elevate crop management, streamline water consumption, and boost productivity among Indian farmers. Discussion: The automated crop monitoring and irrigation system has transformative potential in farming. Some future scope and enhancements may include broadening crop compatibility, integrating satellite data, enhancing pest monitoring, improving connectivity, enriching the mobile app, scaling up through partnerships, and refining the predictive models. Conclusions: The IoT-driven crop monitoring system revolutionizes Indian agriculture by optimizing irrigation and integrating weather forecasts. With mobile app enhancements and future improvements, it promises sustainable farming and empowerment for farmers.

DNN model reveals sharp decline in PM2.5 concentration in the Yangtze River Delta during COVID-19 lockdown and lift lockdown

The COVID-19 lockdown in early 2020 and subsequent lifting in late 2022 had a significant impact on air pollution levels in the Yangtze River Delta (YRD). Previous studies have not provided a clear understanding of the detailed spatiotemporal characteristics of PM2.5 concentrations in various functional areas of cities during different periods before and after the outbreak of the epidemic. However, by employing a deep neural network (DNN) model and integrating satellite data, meteorological reanalysis, and PM2.5 observations, established an estimation of high-resolution PM2.5 distribution during the period from 2019 to 2022. The DNN model performed well (R2 = 0.78). During the lockdown, PM2.5 concentrations in 14 YRD cities were over 50% lower than in previous years. Interestingly, even after the lockdown was lifted, PM2.5 levels remained relatively low due to reduced human activities caused by widespread infections. Found that PM2.5 reductions varied across different intra-city functional regions during both the lockdown and lift lockdown periods. Overall, the changes in PM2.5 levels during the 2022 lift lockdown were smaller than during the 2020 lockdown. These findings emphasize the need for tailored government policies to address COVID-19's impact on air pollution, considering diverse functional areas within the region.

Integration of satellite remote sensing and MaxEnt modeling for improved detection and management of forest pests.

Forest pests pose a major threat to ecosystem services worldwide, requiring effective monitoring and management strategies. Recently, satellite remote sensing has emerged as a valuable tool to detect defoliation caused by these pests. Lymantria dispar, a major forest pest native to Japan, Siberia, and Europe, as well as introduced regions in North America, is of particular concern. In this study, we used Sentinel-2 satellite imagery to estimate the defoliation area and predict the distribution of L. dispar in Toyama Prefecture, central Japan. The primary aim was to understand the spatial distribution of L. dispar. The normalized difference vegetation index (NDVI) difference analysis estimated a defoliation area of 7.89 km2 in Toyama Prefecture for the year 2022. MaxEnt modeling, using defoliation map as occurrence data, identified the deciduous forests between approximately 35° and 50° at elevations of 400m and 700m as highly suitable for L. dispar. This predicted suitability was also high for larval locations but low for egg mass locations, likely due to differences in larval habitats and ovipositing sites. This study is the first attempt to utilize NDVI-based estimates as a proxy for MaxEnt. Our results showed higher prediction accuracy than a previous study based on the occurrence records including larvae, adults, and egg masses, indicating better discrimination of the distribution of L. dispar defoliation. Therefore, our approach to integrating satellite data and species distribution models can potentially enhance the assessment of areas affected by pests for effective forest management.

The effects of non-local observations on the adjoint estimation of local model parameters: An example of Manning’s n coefficient in a tidal model over the Bohai, Yellow, and East China Seas

Accurate parameter estimation is a key issue for enhancing the performance of hydrological models. With the rapid development of satellite technology, integrating satellite data and numerical modelling for parameter estimation has gained more prominence. The limited spatial coverage of altimeters necessitates areas without direct local observations to rely only on information from nearby non-local observations. However, the relation is far from clear between non-local observations and the estimation of local model parameters. In this study, a two-dimensional adjoint tidal model over the Bohai, Yellow, and East China Seas (BYECS) is developed, assimilating observations from TOPEX/Poseidon, Jason-1, and Jason-2 altimeters in conjunction with tide-gauge stations. In twin experiments, the feasibility and reliability of utilizing non-local observations are emphasized by varying synthetic observations. The experiments also reveal how the number and distance of non-local observations affect the ill-posedness of local parameter estimation. The estimation errors can be reduced by increasing observations within a ‘critical distance’, beyond which the accuracy does not improve further. Subsequently, the robustness of ‘critical distance’ is discussed under different prescribed parameter distributions, sizes of predefined optimized area, and random observational errors, indicating that the ‘critical distance’ is approximately 1.0°-2.0°. These results provide a positive reference for practical experiment. In BYECS, the order of Manning’s n coefficient ranges from 10-4 to 10-1, with an average value of 0.0246 in shallow waters. The spatial distribution reveals 9 high-value areas, primarily modulated by a concurrence of sandy sediment and weak tidal currents. This study offers valuable insights into refining the adjoint model for physical parameter estimation, particularly in anticipation of the expanded spatial coverage of SWOT. Compared to only assimilating T/P series altimeters, incorporating SWOT reduces discrepancies by over 38%. Additionally, the spatial Manning’s n coefficient provides guidance for enhancing tidal simulation in other models.

AttUnet_R_SFT: A Novel Network to Explore the Application of Complex Terrain Information in Satellite Precipitation Estimating

AbstractAccurate rainfall measurement with a precise spatial and temporal resolution is essential for making informed decisions during disasters and conducting scientific studies, particularly in regions characterized by intricate terrain and limited coverage of automated weather stations. Retrieval of precipitation with satellite is currently the most effective means to obtain precipitation over large‐scale areas. The key to enhancing the accuracy of precipitation estimation and forecasting in regions with complex terrain lies in effectively integrating satellite data with topographic information. This paper introduces a deep learning approach called AttUnet_R_SFT that utilizes high temporal, spatial, and spectral resolution data obtained from the Fengyun 4A satellite, and incorporates the Deep Spatial Feature Transform (SFT) layer to incorporate geographical data for estimating half‐hourly precipitation in northeastern China. We assess it by compared to operational near‐real‐time satellite precipitation products demonstrated to be successful in estimating precipitation and baseline deep learning models. According to the experimental findings, the AttUnet_R_SFT model outperforms practical precipitation products and baseline deep learning models in both identifying and estimating precipitation. The main enhancement of the model performance is shown in the windward slope of the Greater Khingan Mountains as a result of the successful incorporation of geographical data. Hence, the suggested framework holds the capability to function as a superior and dependable satellite‐derived precipitation estimation solution in regions characterized by intricate terrain and infrequent rainfall. The findings of this study indicate that the utilization of deep learning algorithms for satellite precipitation estimation shows potential as a fruitful avenue for further research.

Mapping Blue Economy Potential Using Spatial Statistical Downscaling Model: Analysis of the Impact of Climate Change on Freshwater Fish Resources

Blue Economy is a sustainable economic concept that focuses on utilizing economic resources in marine, coastal and land ecosystems. Sustainable use of freshwater resources in the blue economy for inland waters supports economic growth with environmental balance. The Statistical Downscaling method is used to understand the impact of climate change on freshwater fish resources. To carry out mapping of the potential of the blue economy, it is carried out by statistical downscaling modeling with satellite variables with Integrated Nested Laplace Approximation parameter estimates. The response variable is satellite variables in the form of average rainfall. The modeling results show that Kalipuro District has the highest blue economy potential, while Kalibaru has the lowest. From the research results, that satellite data on average rainfall is a strong basis for printing statistical downscaling, increasing efficiency with open source digital data sources. Satellite data integration, maximizing analysis and comprehensive blue economy potential efficiency.

Comparison of three machine learning algorithms for retrieving soil moisture information from Sentinel-1A SAR data in northwest Shandong plain, China

Soil moisture (SM) plays a critical role in the growth and management of grain in semi-humid regions. However, little is known about how to integrate satellite data with machine learning to accurately retrieve SM information in these areas. This study compares the capability of three machine learning algorithms, Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN), to extract SM information over the Northwest Shandong Plain using multi-phase dual-polarized Sentinel-1A satellite data. The backscattering coefficients were obtained through standard intensity and phase processing to calculate the SAR indices, and several characteristic parameters were extracted as impact factors using the Cloude-Pottier decomposition. The importance of these factors was analyzed, while the performance of each machine learning algorithm was comprehensively evaluated using the K-fold cross-validation method. The best-performing model was utilized to retrieve the spatio-temporal changes in SM in the study area. The findings indicate the following: (1) The first eigenvalue has the greatest impact on retrieval accuracy, followed by entropy, where the intensity component of Shannon's entropy is more important than its polarization component; (2) The addition of more impact factors does not bring a continuous improvement in model performance, but the optimal factor combinations differ for different machine learning retrieval models; (3) The RF model trained using the IM12 combination demonstrates better performance than SVM and ANN in retrieving SM information, with a coefficient of determination (R2) of 0.55 and a root mean square error of 6.12 vol% on the validation set. The level of SM in the Yellow River National Wetland Park is higher than that of the surrounding areas, with substantial seasonal changes. Precipitation, temperature, and vegetation significantly influence the regional variations in SM at the macroscopic level.

Irrigation Quantification Through Backscatter Data Assimilation With a Buddy Check Approach

AbstractIrrigation is an important component of the terrestrial water cycle, but it is often poorly accounted for in models. Recent studies have attempted to integrate satellite data and land surface models via data assimilation (DA) to (a) detect and quantify irrigation, and (b) better estimate the related land surface variables such as soil moisture, vegetation, and evapotranspiration. In this study, different synthetic DA experiments are tested to advance satellite DA for the estimation of irrigation. We assimilate synthetic Sentinel‐1 backscatter observations into the Noah‐MP model coupled with an irrigation scheme. When updating soil moisture, we found that the DA sets better initial conditions to trigger irrigation in the model. However, DA updates to wetter conditions can inhibit irrigation simulation. Building on this limitation, we propose an improved DA algorithm using a buddy check approach. The method still updates the land surface, but now the irrigation trigger is not primarily based on the evolution of soil moisture, but on an adaptive innovation (observation minus forecast) outlier detection. The new method was found to be optimal for more temperate climates where irrigation events are less frequent and characterized by higher application rates. It was found that the DA outperforms the model‐only 14‐day irrigation estimates by about 20% in terms of root‐mean‐squared differences, when frequent (daily or every other day) observations are available. With fewer observations or high levels of noise, the system strongly underestimates the irrigation amounts. The method is flexible and can be expanded to other DA systems, also real‐world cases.