Land Cover Classification Research Articles

Automating band selection for hyperspectral indices: bridging AVIRIS-NG and Sentinel-2 satellite data for earth science applications

Hyperspectral data from the Airborne Visible and Infra-Red Imaging Spectrometer – Next-Generation (AVIRIS-NG) offers transformative potential for Earth science research, enabling detailed analysis of land surface processes, resource monitoring, and environmental dynamics. This study presents an automated methodology to optimize the selection of AVIRIS spectral bands, improving the computation of indices critical to Earth science applications. By leveraging multiple hyperspectral bands, the approach enhances the accuracy of indices used to monitor water resources, vegetation health, urban expansion, and built-up areas. The methodology involves calculating indices from all possible AVIRIS band combinations, evaluating their root mean squared error (RMSE) against Sentinel-2 indices, reducing RMSE skewness, and selecting bands with minimal deviation for specific Land Use Land Cover (LULC) categories. The process is automated and employs parallel processing with Python, significantly reducing execution time and enabling scalability for large geospatial datasets. Key indices, including the Normalized Difference Water Index (NDWI), Normalized Difference Red Edge (NDRE), and Normalized Difference Built-up Index (NDBI), Green Normalized Difference Vegetation Index (GNDVI) were validated using the proposed methodology. Results demonstrate the potential of hyperspectral data to outperform traditional single-band approaches, providing more precise and reliable assessments.

Harnessing Spectral Libraries From AVIRIS-NG Data for Precise PFT Classification: A Deep Learning Approach.

The generation of spectral libraries using hyperspectral data allows for the capture of detailed spectral signatures, uncovering subtle variations in plant physiology, biochemistry, and growth stages, marking a significant advancement over traditional land cover classification methods. These spectral libraries enable improved forest classification accuracy and more precise differentiation of plant species and plant functional types (PFTs), thereby establishing hyperspectral sensing as a critical tool for PFT classification. This study aims to advance the classification and monitoring of PFTs in Shoolpaneshwar wildlife sanctuary, Gujarat, India using Airborne Visible/Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) and machine learning techniques. A comprehensive spectral library was developed, encompassing data from 130 plant species, with a focus on their spectral features to support precise PFT classification. The spectral data were collected using AVIRIS-NG hyperspectral imaging and ASD Handheld Spectroradiometer, capturing a wide range of wavelengths (400-1600 nm) to encompass the key physiological and biochemical traits of the plants. Plant species were grouped into five distinct PFTs using Fuzzy C-means clustering. Key spectral features, including band reflectance, vegetation indices, and derivative/continuum properties, were identified through a combination of ISODATA clustering and Jeffries-Matusita (JM) distance analysis, enabling effective feature selection for classification. To assess the utility of the spectral library, three advanced machine learning classifiers-Parzen Window (PW), Gradient Boosted Machine (GBM), and Stochastic Gradient Descent (SGD)-were rigorously evaluated. The GBM classifier achieved the highest accuracy, with an overall accuracy (OAA) of 0.94 and a Kappa coefficient of 0.93 across five PFTs.

Assessing spatially explicit long-term landscape dynamics based on automated production of land category layers from Danish late nineteenth-century topographic maps in comparison with contemporary maps

Historical topographical maps contain valuable, spatially and thematically detailed information about past landscapes. Yet, for analyses of landscape dynamics through geographical information systems, it is necessary to “unlock” this information via map processing. For two study areas in northern and central Jutland, Denmark, we apply object-based image analysis, vector GIS, colour image segmentation, and machine learning processes to produce machine-readable layers for the land use and land cover categories forest, wetland, heath, dune sand, and water bodies from topographic maps from the late nineteenth century. Obtained overall accuracy was 92.3%. A comparison with a contemporary map revealed spatially explicit landscape dynamics dominated by transitions from heath and wetland to agriculture and forest and from heath and dune sand to forest. However, dune sand was also characterised by more complex transitions to heath and dry grassland, which can be related to active prevention of sand drift but that can also be biased by different categorisations of dune sand between the historical and contemporary data. We conclude that automated production of machine-readable layers of land use and land cover categories from historical topographical maps offers a resource-efficient alternative to manual vectorisation and is particularly useful for spatially explicit assessments of long-term landscape dynamics. Our results also underline that an understanding of mapped categories in both historical and contemporary maps is critical to the interpretation of landscape dynamics.Graphical abstract

Prediction of Land Image Classification using Squeeze Synchronization layer and Convolve Craft Focus Module in ResNet 101 Model

The classification of image is essential to make LULC (Land Use Land Cover) maps. However, the classification of land cover plays a vital role for studying and modernizing the land areas. Recently, deep learning (DL) techniques have achieved outstanding performance in the classification of high-resolution images. Different techniques have been employed in traditional methods to identify LULC due to its complex and ever-changing nature. However, these studies have shown improved outcomes despite some restrictions such as inaccuracies and reduced performance. To address these problems, the proposed study introduces a Squeeze Synchronization Layer (SSL) and a Convolve Craft Focus Module (CCFM) where, SSL reduces input data complexity by removing noise and irrelevant information from images using pooling and convolutional operations also, CCFM enhances feature extraction to improve land classification accuracy. The EUROSAT land image dataset is utilized for the evaluation of the introduced model. Whereas, the dataset comprises of 64x64 images, which are captured by satellite Sentinel-2A in ResNet 101 input layer. Although, a SSL is suggested, and a CCFM is implemented in the convolutional layer for classifying land images. However, the efficiency of the system is evaluated by measuring performance metrics such as recall, F1-score, precision, and accuracy values of the proposed system. The accuracy value of the proposed system is 96% of accuracy, 100% of precision, 100% of recall, and 100% of F1-score, signifies the superior efficiency of the proposed model

Application of UAV Photogrammetry and Multispectral Image Analysis for Identifying Land Use and Vegetation Cover Succession in Former Mining Areas

Variations in vegetation indices derived from multispectral images and digital terrain models from satellite imagery have been successfully used for reclamation and hazard management in former mining areas. However, low spatial resolution and the lack of sufficiently detailed information on surface morphology have restricted such studies to large sites. This study investigates the application of small, unmanned aerial vehicles (UAVs) equipped with multispectral sensors for land cover classification and vegetation monitoring. The application of UAVs bridges the gap between large-scale satellite remote sensing techniques and terrestrial surveys. Photogrammetric terrain models and orthoimages (RGB and multispectral) obtained from repeated mapping flights between November 2023 and May 2024 were combined with an ALS-based reference terrain model for object-based image classification. The collected data enabled differentiation between natural forests and areas affected by former mining activities, as well as the identification of variations in vegetation density and growth rates on former mining areas. The results confirm that small UAVs provide a versatile and efficient platform for classifying and monitoring mining areas and forested landslides.

Pyramid Fine and Coarse Attentions for Land Cover Classification from Compact Polarimetric SAR Imagery

Land cover classification from compact polarimetry (CP) imagery captured by the launched RADARSAT Constellation Mission (RCM) is important but challenging due to class signature ambiguity issues and speckle noise. This paper presents a new land cover classification method to improve the learning of discriminative features based on a novel pyramid fine- and coarse-grained self-attention transformer (PFC transformer). The fine-grained dependency inside a non-overlapping window and coarse-grained dependencies between non-overlapping windows are explicitly modeled and concatenated using a learnable linear function. This process is repeated in a hierarchical manner. Finally, the output of each stage of the proposed method is spatially reduced and concatenated to take advantage of both low- and high-level features. Two high-resolution (3 m) RCM CP SAR scenes are used to evaluate the performance of the proposed method and compare it to other state-of-the-art deep learning methods. The results show that the proposed approach achieves an overall accuracy of 93.63%, which was 4.83% higher than the best comparable method, demonstrating the effectiveness of the proposed approach for land cover classification from RCM CP SAR images.

Comparison of Tree Typologies Mapping Using Random Forest Classifier Algorithm of PRISMA and Sentinel-2 Products in Different Areas of Central Italy

The continuous development of satellite imagery, coupled with advancements in machine learning technologies, allows detailed mapping of terrestrial landscapes. This study evaluates the classification performance of tree typologies using Sentinel-2 and PRISMA data, focusing on central Italy’s different areas. The purpose is to assess the role of spectral and spatial resolution in land cover classification, contributing to forest management and conservation efforts. Random Forest Classifier was applied to classify tree typologies across two study areas: the Roman Coastal region and the Lake Vico Basin. Ground truth (GT) data, collected from a trial citizen survey campaign, were used for training and validation. PRISMA datasets, particularly when processed with PCA, consistently outperformed Sentinel-2. The PRISMA PCA dataset achieved the highest overall accuracy with 71.09% for the Roman Coastal region and 87.15% for the Lake Vico Basin, emphasizing the value of spectral resolution. However, Sentinel-2 showed comparative strength in spatially heterogeneous areas. Tree typologies with more uniform distribution, such as hazelnut and chestnut, achieved higher classification accuracy compared to mixed-species forests. The study assesses that Sentinel-2 remains a viable alternative where spatial resolution is critical also considering the limited PRISMA images’ availability. Moreover, the work explores the potential of combining satellites and accurate GT for improved land cover mapping.

Environmental impacts of urban growth and land use changes in tropical cities

Urban centers across the globe are undergoing rapid land use changes due to population growth, economic development, and urbanization. These changes have a profound impact on environmental dynamics and urban livelihoods. This study investigates land use changes and their environmental implications on urban livelihoods in Iwo, Nigeria. The research explores the patterns and drivers of land use changes over the past four decades and evaluates their effects on environmental quality and urban livelihoods. A combination of remote sensing and survey methods was employed. Landsat images from 1982 to 2023 were analyzed using supervised classification techniques to map changes in land cover categories such as built-up areas, vegetation, farmland, bare land, and water bodies. Additionally, a survey was conducted with 550 residents, selected through simple random sampling, to identify the key drivers of urban expansion from the residents’ perspectives. Descriptive analysis revealed that most respondents had lived in Iwo for over 30 years, with many engaged in farming, trading, and civil service. Factor analysis was used to identify significant variables driving urban growth. The results indicate a substantial increase in built-up areas, from 9.30 km2 in 1982 to 30.69 km2 in 2023, alongside a significant decrease in vegetation cover. Farmland area showed an increasing trend, while bare land decreased. Key drivers of urban growth identified include religious activities, availability of land resources, small-scale businesses, government initiatives, and educational institutions. The environmental implications include deforestation, reduced green spaces, increased surface runoff, and pollution, which affect air quality, water resources, and biodiversity. This study highlights the importance of sustainable urban planning to balance growth with environmental preservation and social equity. The implementation of green infrastructure, effective waste management, and comprehensive urban planning policies is crucial to enhancing resilience and quality of life in Iwo.

Interchangeability of Cross-Platform Orthophotographic and LiDAR Data in DeepLabV3+-Based Land Cover Classification Method

Riverine environmental information includes important data to collect, and the data collection still requires personnel’s field surveys. These on-site tasks still face significant limitations (i.e., hard or danger to entry). In recent years, as one of the efficient approaches for data collection, air-vehicle-based Light Detection and Ranging technologies have already been applied in global environmental research, i.e., land cover classification (LCC) or environmental monitoring. For this study, the authors specifically focused on seven types of LCC (i.e., bamboo, tree, grass, bare ground, water, road, and clutter) that can be parameterized for flood simulation. A validated airborne LiDAR bathymetry system (ALB) and a UAV-borne green LiDAR System (GLS) were applied in this study for cross-platform analysis of LCC. Furthermore, LiDAR data were visualized using high-contrast color scales to improve the accuracy of land cover classification methods through image fusion techniques. If high-resolution aerial imagery is available, then it must be downscaled to match the resolution of low-resolution point clouds. Cross-platform data interchangeability was assessed by comparing the interchangeability, which measures the absolute difference in overall accuracy (OA) or macro-F1 by comparing the cross-platform interchangeability. It is noteworthy that relying solely on aerial photographs is inadequate for achieving precise labeling, particularly under limited sunlight conditions that can lead to misclassification. In such cases, LiDAR plays a crucial role in facilitating target recognition. All the approaches (i.e., low-resolution digital imagery, LiDAR-derived imagery and image fusion) present results of over 0.65 OA and of around 0.6 macro-F1. The authors found that the vegetation (bamboo, tree, grass) and road species have comparatively better performance compared with clutter and bare ground species. Given the stated conditions, differences in the species derived from different years (ALB from year 2017 and GLS from year 2020) are the main reason. Because the identification of clutter species includes all the items except for the relative species in this research, RGB-based features of the clutter species cannot be substituted easily because of the 3-year gap compared with other species. Derived from on-site reconstruction, the bare ground species also has a further color change between ALB and GLS that leads to decreased interchangeability. In the case of individual species, without considering seasons and platforms, image fusion can classify bamboo and trees with higher F1 scores compared to low-resolution digital imagery and LiDAR-derived imagery, which has especially proved the cross-platform interchangeability in the high vegetation types. In recent years, high-resolution photography (UAV), high-precision LiDAR measurement (ALB, GLS), and satellite imagery have been used. LiDAR measurement equipment is expensive, and measurement opportunities are limited. Based on this, it would be desirable if ALB and GLS could be continuously classified by Artificial Intelligence, and in this study, the authors investigated such data interchangeability. A unique and crucial aspect of this study is exploring the interchangeability of land cover classification models across different LiDAR platforms.

Redução da complexidade na classificação de LULC para uma melhor transferibilidade metodológica

Many studies have been made in order to shorten the distance between satellite imagery processing and water resources management as regards land use/land cover classes and image classification for environmental physics-based hydrological models. The question raised from these studies was how to relate the models’ curve numbers and CP factors into a semantic hierarchical network, including the most used and relevant land cover classes, and then classify them. To achieve the creation and classification of the semantic hierarchical network, a dense review of and comparison between land use/ land cover classes used for environmental physics-based models were made as a first step. Then, a wrapper model for feature selection and the object-based image analysis (OBIA) approach were applied to classify the two high-spatial-resolution mosaic images of the Vossoroca basin study area. The findings showed the almost direct relation between the curve numbers or CP factors and the land use/ land cover classes already developed by relevant international agencies such as CORINE and LCCS. In addition, a satisfactory overall image classification accuracy larger than 88% was revealed when using the developed feature selection method along with the OBIA approach using the nearest neighbor as classifier.

GIS-based Classification of Habitat, Land Use, and Land Cover in Several Creeks within Sindh Province's Indus Delta

GIS-based Classification of Habitat, Land Use, and Land Cover in Several Creeks within Sindh Province's Indus Delta

Predictive modeling of land cover changes in round-1 smart cities of India using cellular automata and GIS

The present study dealt with the Land Use Land Cover (LULC) and built-up dynamics for four round-1 smart cities within a period of 20 years (2001–2021) using satellite-based remote sensing and Geographic Information System (GIS) techniques. The study also presented predictive aspects of built-up dynamics by the year 2031. Various layers contribute to urban growth viz. slope, population density, distance to Central Business District (CBD), major roads, and drainage were analyzed and prepared. The Cellular Automata (CA) model was applied using the previous years’ layers and the thematic ones to predict the spatial extent of the year 2031. Thresholds for all thematic layers based on spatial proximity were selected for various classes of these factors. Built-up change rate for all the four round-1 smart cities viz. Ahmedabad (the year 2001 ~ 183.79 km2, the year 2021 ~ 252.3 km2), Chennai (the year 2001 ~ 102.45 km2, the year 2021 ~ 137.07 km2), Jaipur (the year 2001 ~ 132.73 km2, the year 2021 ~ 221.71 km2) and Surat (the year 2001 ~ 97.73 km2, the year 2021 ~ 158.79 km2) has shown a dynamic growth from 2001–2021. The study also revealed transition states of land cover classes between 2021 and 2031. The comparison between actual and simulated changes for the year 2021 showed the model’s accuracy assessment. The estimates also revealed a continuous increment in the impervious state of the urban surface due to urban expansion. Thus, satellite image-based LULC classification, built-up mapping, and model-based prediction could be utilized for planning infrastructure development.

Comprehensive dataset from high resolution UAV land cover mapping of diverse natural environments in Serbia

This study highlights the vital role of high-resolution (HR), open-source land cover maps for food security, land use planning, and environmental protection. The scarcity of freely available HR datasets underscores the importance of multi-spectral HR aerial images. We used unmanned aerial vehicle (UAV) to capture images for a centimeter-level orthomosaics, facilitating advanced remote sensing and spatial analysis. Our method compares the efficacy and accuracy of object-based image analysis (OBIA) combined with random forest and convolutional neural networks (CNN) for land cover classification. We produced detailed land cover maps for 27 varied landscapes across Serbia, identifying nine unique land cover classes and assessing human impact on natural habitats. This resulted in a valuable dataset of HR multi-spectral orthomosaics across ecological zones, alongside land cover classification with extensive metrics and training data for each site. This dataset is a valuable resource for researchers working on habitats mapping and assessment for biodiversity monitoring studies on one side and researchers working on novel machine learning methods for land cover classification.

Assessing the impacts of forest cover change on carbon stock and soil moisture dynamics using geospatial techniques: a case study of Nensebo forest, Southern Ethiopia.

Assessing the impacts of forest cover change on carbon stock and soil moisture dynamics is critical for understanding environmental degradation and guiding sustainable land management. This study evaluates the effects of forest cover change on carbon stock and soil moisture dynamics in Nensebo Forest from 1993 to 2023 using geospatial techniques. Landsat imagery including TM (1993), ETM + (2009), and OLI/TIRS (2023) were used. Land use land cover (LULC) classification was performed using supervised classification approach with maximum likelihood algorithm. The study reveals that agricultural land expanded significantly from 143.2 km2 (21.8%) to 230.0 km2 (35.1%), along with increases in bare land and grassland. Moreover, result reveals a substantial decline in vegetation health (forest), with the Normalized Difference Vegetation Index (NDVI) decreasing from 0.78 in 1993 to 0.55 in 2023, indicating anincrease ofdeforestation and land degradation. The soil moisture index (SMI) shows a reduction in soil moisture retention from 0.51 to 0.39, reflecting the adverse impact of forest loss on soil moisture dynamics. Carbon stock analysis reveals a dramatic decrease in forest area from 489.5 to 220.5 km2, leading to increased carbon dioxide emissions from forest loss, which rose from 293.03 tons to 1550.34 tons. The study underscores the urgent need for integrated land management strategies that balance agricultural development with ecological conservation. Therefore, to mitigate climate change and maintain ecological stability, the study recommends implementing sustainable land use practices, promoting reforestation, and developing environmental relatedpolicies to preserve the remaining forest cover while supporting agricultural productivity.

Comparative Analysis of Ecological Restoration Methods Applied to Rehabilitate Mining Sites: A Case Study of the Fushun and Pingshuo Mining Sites in China Using Remote Sensing Techniques Between 2000 and 2024

This study presents a comparative analysis of ecological restoration methods employed to rehabilitate mining sites, focusing on the Fushun and Pingshuo mining areas in China. Given the significant environmental degradation which has resulted from the mining activities. Effective restoration strategies are essential for enhancing biodiversity and ecological integrity. This research evaluates changes in vegetation cover and environmental health at both sites while employing metrics such as the Normalized Difference Vegetation Index (NDVI) and land cover classification utilizing remote sensing techniques. This study addresses three primary objectives which are: assessing vegetation recovery post-restoration, analyzing soil and water quality improvements, and comparing the effectiveness of various restoration methods. Preliminary findings indicate that while both sites have achieved notable vegetation recovery, differences in restoration techniques, regulatory frameworks, and environmental conditions influence outcomes. This research takes into account the important role of remote sensing in monitoring restoration success and informs best practices for future ecological restoration initiatives in mining-affected regions.

Remote Sensing Based Land Cover Classification Using Residual Feature—Hyper Graph Convolutional Neural Network (HGCNN)

Remote Sensing Based Land Cover Classification Using Residual Feature—Hyper Graph Convolutional Neural Network (HGCNN)

Applicability of reanalysis data in calibrating a hydrological model in a data-scarce mountainous watershed

ABSTRACT Understanding the hydrological processes of mountainous regions is crucial for watershed management. The increased frequency of floods in the Himalayan region emphasizes the need to set up a hydrological model in this region. The complex topography and climate patterns of the Himalayas, with a few hydrometeorological stations, make modeling the region challenging. Therefore, the study of hydrological responses using a fully distributed hydrological model in this region is very rare. This study aims to address the challenges of data scarcity in mountain regions using alternative data for observed discharge data for the calibration of the hydrological model. We assess the utility of reanalysis surface runoff data (RSRD) from ERA-5 in calibrating a fully distributed hydrological model WATFLOOD. Six water balance components at nine land-cover classes are analyzed using the WATFLOOD model. The results show that the RSRD can be used as an alternative for the discharge data for calibration of the hydrological model. The evaluation of water balance components shows changes corresponding to wet and dry years. We verified simulation results using observed data, revealing the limitations of calibrating a hydrological model with RSRD.

Lightweight Deep Learning Model, ConvNeXt-U: An Improved U-Net Network for Extracting Cropland in Complex Landscapes from Gaofen-2 Images.

Extracting fragmented cropland is essential for effective cropland management and sustainable agricultural development. However, extracting fragmented cropland presents significant challenges due to its irregular and blurred boundaries, as well as the diversity in crop types and distribution. Deep learning methods are widely used for land cover classification. This paper proposes ConvNeXt-U, a lightweight deep learning network that efficiently extracts fragmented cropland while reducing computational requirements and saving costs. ConvNeXt-U retains the U-shaped structure of U-Net but replaces the encoder with a simplified ConvNeXt architecture. The decoder remains unchanged from U-Net, and the lightweight CBAM (Convolutional Block Attention Module) is integrated. This module adaptively adjusts the channel and spatial dimensions of feature maps, emphasizing key features and suppressing redundant information, which enhances the capture of edge features and improves extraction accuracy. The case study area is Hengyang County, Hunan Province, China, using GF-2 remote sensing imagery. The results show that ConvNeXt-U outperforms existing methods, such as Swin Transformer (Acc = 85.1%, IoU = 79.1%), MobileNetV3 (Acc = 83.4%, IoU = 77.6%), VGG16 (Acc = 80.5%, IoU = 74.6%), and ResUnet (Acc = 81.8%, IoU = 76.1%), achieving an IoU of 79.5% and Acc of 85.2%. Under the same conditions, ConvNeXt-U has a faster inference speed of 37 images/s, compared to 28 images/s for Swin Transformer, 35 images/s for MobileNetV3, and 0.43 and 0.44 images/s for VGG16 and ResUnet, respectively. Moreover, ConvNeXt-U outperforms other methods in processing the boundaries of fragmented cropland, producing clearer and more complete boundaries. The results indicate that the ConvNeXt and CBAM modules significantly enhance the accuracy of fragmented cropland extraction. ConvNeXt-U is also an effective method for extracting fragmented cropland from remote sensing imagery.

Use of the LCM Model in the prospective simulation of land use in the Nafoun watershed (Northern Ivory Coast)

Land use change is known worldwide as a driver of environmental change. Environmental change assessment is the most accurate method for understanding land use, the types of change to be estimated, and the forces and evolutions driving these changes. The aim of the study is to assess the temporal and spatial dynamics of land use change and to predict the future using Landsat images. The Land Change Modeler (LCM) was therefore used. LCM is a module integrated into a Geographic Information System (GIS) and TerrSet geospatial modeling system, assimilated to the Multi- Layer Perceptron (MLP) and the CA_Markov chain for analysis and prediction of land use change and assessment of environmental implications. LCM forward modeling relies on two types of input maps: (1) land cover maps at previous times and (2) explanatory variable maps. Our study area is the Nafoun watershed in the Poro region of northern Côte d'Ivoire. Landsat images from 1986, 2000 and 2023 were used to assess and predict the spatio- temporal distributions of land use change. The historical results show that from 1986 to 2023, two trends were observed in the evolution of the different land cover classes in the Nafoun watershed. The first trend is regressive and concerns forests, savannahs, water and habitats/bare ground. The second trend is progressive and concerns crops, whose surface area has practically increased tenfold, from 8.31 to 78.15 km2. The land-use map of the Nafoun watershed to 2070 in the deforestation scenario shows a trend towards an increase in agricultural areas and bare habitats/soils, and a decrease in savannah, forest and water areas. However, in the reforestation scenario, the forest and savannah class have increased significantly, while the area of habitats/bare ground has decreased. In this scenario, a sound environmental protection policy would play a positive role in the conservation of natural plant resources.

Novel Bat-Monitoring Dataset Reveals Targeted Foraging With Agricultural and Pest Control Implications.

Quantifying ecosystem services provided by mobile species like insectivorous bats remains a challenge, particularly in understanding where and how these services vary over space and time. Bats are known to offer valuable ecosystem services, such as mitigating insect pest damage to crops, reducing pesticide use, and reducing nuisance pest populations. However, determining where bats forage is difficult to monitor. In this study, we use a weather-radar-based bat-monitoring algorithm to estimate bat foraging distributions during the peak season of 2019 in California's Northern Central Valley. This region is characterized by valuable agricultural crops and significant populations of both crop and nuisance pests, including midges, moths, mosquitos, and flies. Our results show that bat activity is high but unevenly distributed, with rice fields experiencing significantly elevated activity compared to other land cover types. Specifically, bat activity over rice fields is 1.5 times higher than over any other land cover class and nearly double that of any other agricultural land cover. While irrigated rice fields may provide abundant prey, wetland and water areas showed less than half the bat activity per hectare compared to rice fields. Controlling for land cover type, we found bat activity significantly associated with higher flying insect abundance, indicating that bats forage in areas where crop and nuisance pests are likely to be found. This study demonstrates the effectiveness of radar-based bat monitoring in identifying where and when bats provide ecosystem services.