Search

Arthropods contribute importantly to ecosystem functioning but remain understudied. This undermines the validity of conservation decisions. Modern methods are now making arthropods easier to study, since arthropods can be mass-trapped, mass-identified, and semi-mass-quantified into 'many-row (observation), many-column (species)' datasets, with homogeneous error, high resolution, and copious environmental-covariate information. These 'novel community datasets' let us efficiently generate information on arthropod species distributions, conservation values, uncertainty, and the magnitude and direction of human impacts. We use a DNA-based method (barcode mapping) to produce an arthropod-community dataset from 121 Malaise-trap samples, and combine it with 29 remote-imagery layers using a deep neural net in a joint species distribution model. With this approach, we generate distribution maps for 76 arthropod species across a 225 km2 temperate-zone forested landscape. We combine the maps to visualize the fine-scale spatial distributions of species richness, community composition, and site irreplaceability. Old-growth forests show distinct community composition and higher species richness, and stream courses have the highest site-irreplaceability values. With this 'sideways biodiversity modelling' method, we demonstrate the feasibility of biodiversity mapping at sufficient spatial resolution to inform local management choices, while also being efficient enough to scale up to thousands of square kilometres. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'. [ABSTRACT FROM AUTHOR]

The application of machine learning (ML) techniques for understanding and predicting organic matter (OM) and harmful algal blooms (HABs) in freshwater systems has increased significantly with the availability of abundant data and advanced monitoring technologies. However, there is a lack of comprehensive reviews concentrating on practical applications and delving into the potential risks associated with misrepresentation or inflation in constructing ML models. This review aims to bridge these gaps by providing a comprehensive overview of various aspects of ML applications in the context of OM and HABs in freshwater systems. It covers practical ML applications for rapid assessment, early warning, and driver analysis, highlighting the diverse range of techniques employed in these areas. Furthermore, it discusses the challenges and considerations associated with data handling, including using in situ and remote sensing data and the importance of appropriate data-splitting techniques to avoid data leakage. To ensure unbiased and reproducible results, this review offers recommendations for model improvement, such as utilizing explainable ML techniques to gain insights into model behavior and avoiding overreliance on a single ML algorithm. It also emphasizes the significance of deploying ML models through user-friendly interfaces, enabling non-experts in ML to effectively utilize these models in real-world water environments. [ABSTRACT FROM AUTHOR]

Greenspaces on university campuses have gained recognition for their multifaceted impact on the physical, social, emotional and intellectual well‐being of students. The allocation of resources towards the development and maintenance of greenspaces is regarded as a strategy in the pursuit of sustainable development goals. However, the research on greenspaces within higher education has been inadequate. This study conducts an assessment of greenspaces within 2556 Chinese universities using remote sensing and geospatial technology, analysing the disparities in their distribution and exploring the spatial patterns and driving factors on a national scale. A national university greenspace database is obtained. Unexpectedly, the study finds that greenspace area and proportion within Chinese universities are relatively low in comparison to the greenspace areas outside the campus and of the city. There is heterogeneity and a decreasing trend in university greenspace. Compared to university faculty and off‐campus population, university students have the lowest per capita greenspace area. Of concern is the significant issue of greenspace inequality. Our research suggests that the inequality in greenspace provision for university students can be explained by factors of economic development, educational investments and provincial greenspace supply. This study provides an in‐depth analysis of the state of greenspaces in Chinese universities and calls for interdisciplinary and interdepartmental cooperation to address issues of greenspace inequality and campus greening, ensuring the sustainability and livability of urban areas and university campuses. [ABSTRACT FROM AUTHOR]

Enviromics refers to the characterization of micro- and macroenvironments based on large-scale environmental datasets. By providing genotypic recommendations with predictive extrapolation at a site-specific level, enviromics could inform plant breeding decisions across varying conditions and anticipate productivity in a changing climate. Enviromics-based integration of statistics, envirotyping (i.e., determining environmental factors), and remote sensing could help unravel the complex interplay of genetics, environment, and management. To support this goal, exhaustive envirotyping to generate precise environmental profiles would significantly improve predictions of genotype performance and genetic gain in crops. Already, informatics management platforms aggregate diverse environmental datasets obtained using optical, thermal, radar, and light detection and ranging (LiDAR)sensors that capture detailed information about vegetation, surface structure, and terrain. This wealth of information, coupled with freely available climate data, fuels innovative enviromics research. While enviromics holds immense potential for breeding, a few obstacles remain, such as the need for (1) integrative methodologies to systematically collect field data to scale and expand observations across the landscape with satellite data; (2) state-of-the-art AI models for data integration, simulation, and prediction; (3) cyberinfrastructure for processing big data across scales and providing seamless interfaces to deliver forecasts to stakeholders; and (4) collaboration and data sharing among farmers, breeders, physiologists, geoinformatics experts, and programmers across research institutions. Overcoming these challenges is essential for leveraging the full potential of big data captured by satellites to transform 21st century agriculture and crop improvement through enviromics. This perspective highlights how high-throughput satellite envirotyping can transform crop improvement by leveraging multi-source remote sensing to achieve detailed genotype-by-environment objectives, acting as a game changer in predicting plant performance across diverse geographic climates. Enviromics studies integrate spatial, time-series, and environmental data with genomics and phenomics, enhancing predictive breeding and enabling targeted genotype selection to maximize productivity under varying conditions. To support adoption and advance the methodology for satellite envirotyping, key challenges include data integration and the development of robust AI models for precise environmental profiling and crop prediction. [ABSTRACT FROM AUTHOR]

Farming management and alterations in land cover play crucial roles in driving changes in biodiversity, ecosystem functioning, and the provision of ecosystem services. Whereas land cover corresponds to the identity of cultivated/non-cultivated ecosystems in the landscape, farming management describes all the components of farming activities within crops and grassland (i.e., farming practices, crop successions, and farming systems). Despite extensive research on the relationship between land cover and biodiversity at the landscape scale, there is a surprising scarcity of studies examining the impacts of farming management on biodiversity at the same scale. This is unexpected given the already recognized field-scale impact on biodiversity and ecosystem services, and the fact that most species move or supplement their resources in multiple patches across agricultural landscapes. We conducted a comprehensive literature review aimed at answering two fundamental questions: (1) What components of farming management are considered at the landscape scale? (2) Does farming management at the landscape scale impact biodiversity and associated ecosystem functions and services? We retrieved 133 studies through a query on the Web of Science, published from January 2005 to December 2021 addressing the broad notion of farming management at the landscape scale. The key findings are as follows: (1) The effect of farming management components at the landscape scale on biodiversity was tackled in only 41 studies that highlighted that its response was highly taxon-dependent. They reported positive effects of organic farming on pollinators, weeds, and birds, as well as positive effects of extensification of farming practices on natural enemies. (2) Most studies focused on the effect of organic farming on natural enemies and associated pests, and reported contrasting effects on these taxa. Our study underscores the challenges in quantifying farming management at the landscape scale, and yet its importance in comprehending the dynamics of biodiversity and related ecosystem services. [ABSTRACT FROM AUTHOR]

AbstractProblem, research strategy, and findingsTakeaway for practiceOne promising policy approach to addressing housing needs is liberalizing accessory dwelling unit (ADU) development. Yet, understanding the impact of such policy efforts is fundamentally constrained by the inability to quantify and characterize unpermitted ADUs, which may expose homeowners and tenants to legal, financial, and safety risks and confound policy evaluations. We addressed this gap by leveraging computer vision and human annotations to estimate the population of detached ADU constructions in San José (CA). Our contributions are threefold: 1) We estimated the proportion of unpermitted ADU constructions from 2016 to 2020; 2) we describe the demographic, housing market, and parcel characteristics associated with these informal ADUs; and 3) we provide a data set of labeled small buildings, excluding unpermitted detections, for further research. We found that informal ADU construction was substantial—approximately three to four informal units for every formal unit—and more likely in more diverse, dense, and overcrowded neighborhoods. Though our study was limited to analyzing detached ADUs during one time period, we set the stage for further investigations of informal housing across different typologies and over time.Our approach demonstrates the promise of computer vision and human annotations to enable more robust, comprehensive, and reliable understanding of actual—not just permitted—housing units. We urge planners and other policymakers to consider the growth patterns of unpermitted ADUs to more optimally and equitably address housing needs. [ABSTRACT FROM AUTHOR]

Cropland non-agriculturalization (CNA) refers to the conversion of cropland into construction land, woodland/garden/grassland, water body, or other non-agricultural land, which ultimately disrupts local agroecosystems and the cultivation and production of crops. Remote sensing technology is an important tool for large-area CNA detection, and remote sensing based methods that can be used for this task include the time-series analysis method and change detection from bi-temporal images. In particular, change detection methods using high-resolution remote sensing imagery have great potential for CNA detection, but enormous challenges do still remain. The large intra-class variance of cropland with different phenological stages and planting patterns leads to cropland areas being difficult to identify effectively, while certain features can be misidentified because they are similar to cropland, resulting in false alarms and missed detections in the results. There is also a lack of large-scale CNA datasets covering multiple change scenarios as data support. To address these problems, a lightweight model focused on CNA detection (CNANet) is proposed in this paper. Specifically, the uniquely crafted represent-consist-enhance (RCE) module is seamlessly integrated between the encoder and decoder components of CNANet to perform a contrast operation on the deep features extracted by the feature extractor. The RCE module is specifically designed to aggregate multiple cropland representations and extend the cropland representations from the confusing background, to achieve the purpose of reducing the intra-class reflectance differences and enhancing the model's perception of cropland. In addition, a large-scale high-resolution cropland non-agriculturalization (Hi-CNA) dataset was built for the CNA identification task, with a total of 6797 pairs of 512 × 512 images with semantic annotations. Compared to the existing datasets, the Hi-CNA dataset has the advantages of multiple phenological stages, multiple change scenarios, and multiple annotation types, in addition to the large data volume. The experimental results obtained in this study show that the benchmark methods tested on the Hi-CNA dataset can all achieve a good accuracy, proving the high-quality annotation of the dataset. The overall accuracy and F1-score of CNANet with the default settings reach 93.81 % and 78.9 %, respectively, achieving a superior accuracy, compared to the other benchmark methods, and demonstrating stronger perception of cropland changes. In addition, in two selected verification regions within the large-scale real-world CNA mapping results, the F1-score is 83.61 % and 50.87 %. The Hi-CNA can be downloaded from http://rsidea.whu.edu.cn/Hi-CNA_dataset.htm. [ABSTRACT FROM AUTHOR]

Urban development in South America has experienced significant growth and transformation over the past few decades. South America's urban development and trees are closely interconnected, and tree cover within cities plays a vital role in shaping sustainable and resilient urban landscapes. However, knowledge of urban tree canopy (UTC) coverage in the South American continent remains limited. In this study, we used high-resolution satellite images and developed a semi-supervised deep learning method to create UTC data for 888 South American cities. The proposed semi-supervised method can leverage both labeled and unlabeled data during training. By incorporating labeled data for guidance and utilizing unlabeled data to explore underlying patterns, the algorithm enhances model robustness and generalization for urban tree canopy detection across South America, with an average overall accuracy of 94.88% for the tested cities. Based on the created UTC products, we successfully assessed the UTC coverage for each city. Statistical results showed that the UTC coverage in South America is between 0.76% and 69.53%, and the average UTC coverage is approximately 19.99%. Among the 888 cities, only 357 cities that accommodate approximately 48.25% of the total population have UTC coverage greater than 20%, while the remaining 531 cities that accommodate approximately 51.75% of the total population have UTC coverage less than 20%. Natural factors (climatic and geographical) play a very important role in determining UTC coverage, followed by human activity factors (economy and urbanization level). We expect that the findings of this study and the created UTC dataset will help formulate policies and strategies to promote sustainable urban forestry, thus further improving the quality of life of residents in South America. [ABSTRACT FROM AUTHOR]

Semantic understanding of high-resolution remote sensing (RS) images is of great value in Earth observation, however, it heavily depends on numerous pixel-wise manually-labeled data, which is laborious and thereby limits its practical application. Semi-supervised semantic segmentation (SSS) of RS images would be a promising solution, which uses both limited labeled data and dominant unlabeled data to train segmentation models, significantly mitigating the annotation burden. The current mainstream methods of remote sensing semi-supervised semantic segmentation (RS-SSS) utilize the hard or soft pseudo-labels of unlabeled data for model training and achieve excellent performance. Nevertheless, their performance is bottlenecked because of two inherent problems: irreversible wrong pseudo-labels and long-tailed distribution among classes. Aiming at them, we propose a decoupled weighting learning (DWL) framework for RS-SSS in this study, which consists of two novel modules, decoupled learning and ranking weighting, corresponding to the above two problems, respectively. During training, the decoupled learning module separates the predictions of the labeled and unlabeled data to decrease the negative impact of the self-training of the wrongly pseudo-labeled unlabeled data on the supervised training of the labeled data. Furthermore, the ranking weighting module tries to adaptively weight each pseudo-label of the unlabeled data according to its relative confidence ranking in its pseudo-class to alleviate model bias to majority classes as a result of the long-tailed distribution. To verify the effectiveness of the proposed DWL framework, extensive experiments are conducted on three widely-used RS semantic segmentation datasets in the semi-supervised setting. The experimental results demonstrate the superiority of our method to some state-of-the-art SSS methods. Our code will be available at https://github.com/zhu-xlab/RS-DWL. [ABSTRACT FROM AUTHOR]

Temporal contexts are essential for the derivation of causally relevant environmental exposure in environmental and public health studies. We argue that the proper temporal contexts need further emphasis in the mobility-oriented research paradigm and articulate this issue using a study in Hong Kong. We use people's exposure to outdoor artificial light at night (ALAN) and green space as two essential examples. We recruited 208 participants from two representative communities in Hong Kong and derived their mobility-oriented environmental exposures from high-resolution remote sensing data and Google Street View imagery. We employed one-standard-deviational ellipses to quantitatively represent participants' activity spaces, and we further used participants' seven-day Global Positioning System trajectories to derive their spatiotemporally weighted exposures to green space and outdoor ALAN in different temporal contexts. Multiple t tests were used to examine the disparities in activity spaces and measured exposures in different temporal contexts, and these exposure measurements were then used to predict people's health outcomes. We found that people's activity spaces are significantly different in size between day and night, for both weekdays and weekends, and in both geographic contexts. We further observed that improper temporal contexts could lead to significantly different environmental exposure levels and causally irrelevant modeling results. [ABSTRACT FROM AUTHOR]

Most urban tree inventories depend on resource-intensive, field-based assessments, which are unevenly distributed in space and time. Recently, these inventories have been conducted using field inventories combined with airborne multispectral, hyperspectral, LiDAR, and spaceborne multispectral remote sensing. Significant advances have been made in urban tree GIS databases and remote sensing methods, which include delineating individual tree crowns, extracting tree species metrics, and employing classification techniques. Generally, remote sensing methods distinguish individual urban trees using either pixel-based or object-based methods, while image classification procedures are typically divided into parametric (e.g., regression-based classification, Bayesian, and principal component analysis) and non-parametric approaches such as machine learning (e.g., random forests support vector machines) and deep learning (e.g., convolutional neural networks). Our synthesis of the current state of science suggests sensors with the highest spatial (m), spectral (bands), and temporal (repeat time) resolutions result in the most accurate tree species identification. Combining airborne LiDAR/hyperspectral or airborne LiDAR/spaceborne high-resolution multispectral sensors yields the highest accuracy for the most diverse urban forests. An object-based non-parametric approach, like a fully convolutional neural network, scores higher in accuracy assessments than pixel-based parametric approaches. Future studies can leverage global/regional GIS field inventory databases to expand the scope of studies within and across multiple cities, utilizing LiDAR and spaceborne sensors. [ABSTRACT FROM AUTHOR]

Ecological value (EV) is a term used to characterize the biotic or abiotic elements of a landscape, excluding human influence. Significant criteria for EV estimation can be grouped into two categories: ecological properties (biodiversity and vulnerability) and functional/structural features (fragmentation, connectivity, and resilience). While various methodological frameworks exist for estimating these criteria, few studies integrate all five criteria, and even fewer compare their results with fieldwork data. The objective of this study was to devise a novel spatial modelling tool for EV estimation based on biodiversity, vulnerability, fragmentation, connectivity, and resilience, utilizing data from Neotropical montane forests in west-central Mexico. The model incorporated data on (i) biodiversity and vulnerability estimated through ecological niche models, (ii) fragmentation and connectivity using landscape spatial patterns, and (iii) resilience estimated through the inverse of the vegetation sensitivity index. The results were then compared with fieldwork data. Natural protected areas within the Neotropical montane forests of west-central Mexico exhibited high EVs; however, a substantial portion of these forests lack legal protection. In terms of vegetation types, cloud and semideciduous forests exhibited the highest EV, emphasizing the urgent need for legal protection of these vital ecosystems. The comparison process demonstrated a moderate to high correlation in some criteria between the spatial and fieldwork data, indicating that the spatial model robustly captured the landscape spatial patterns. The spatial modelling tool proposed in this study is not only practical but also reproducible and applicable globally. Its efficacy lies in combining ecological properties with the functional and structural features of the landscape, making it particularly suitable for delineating protected natural areas and contributing to landscape planning efforts. [ABSTRACT FROM AUTHOR]

Remote sensing plays an important role for modern geography and environmental science. At the same time, it often stands on a weak epistemological foundation. Remote sensing results are mostly treated as strictly objective, context-independent artifacts. This vastly ignores the human practices that led to these results. Thus, remote sensing data are uncritically incorporated into (environmental) policy decision-making processes without understanding exactly how they were generated. Recent research has been critical of this. In a previous study, I showed that the accuracy of land use results can be increased by class aggregation, while the geographic or environmental meaning of the results suffers. I called this provocatively the "more accurate, less meaningful (MALM)" effect and showed that it exists regardless of the technical level of classification. In this study, I discuss the extent to which MALM can be remedied by choosing an appropriate quality indicator. I show that, to the largest extent conceivable, the quality indicator does not and cannot unveil the effects of socio-technical practices, which are materially inscribed into land use maps. Hence, quality indicators are unable to objectivize the effects of practices and values by the researchers. Consequently, they do not solve the MALM problem. On the contrary, I show that the explicit inclusion of geographic knowledge in quality addresses the MALM effect to the largest extent possible. This reinforces my claim that more attention needs to be paid to considering the values and practices behind remote sensing information. I discuss the results in a broad context and argue that and why critical remote sensing based on critical (physical) geography and science-and-technology studies is vital to better incorporate such results into policymaking. [ABSTRACT FROM AUTHOR]

Mediterranean Europe is experiencing a rise in severe wildfires, resulting in growing socioeconomic and ecological impacts. Postfire restoration has become a crucial approach to mitigate these impacts and promote ecosystem recovery. However, the ecological effects of such interventions are still not well understood. We employed remote sensing techniques to evaluate the impact of postfire emergency stabilization on the recovery of deciduous oak forests in Portugal. Our study encompassed 3013 sampling points located in areas with and without postfire interventions. We chose the Normalized Difference Vegetation Index (NDVI) as an indicator of oak forest recovery over a four-year period following wildfires that took place in 2016 and 2017. We used a Generalized Additive Mixed Model (GAMM) to assess how NDVI changed over time as a function of postfire restoration, fire characteristics, topography, and postfire drought events. We found that postfire restoration had a significant positive effect on NDVI recovery over time, although this effect was small. Severe drought and fire recurrence up to six fires had a negative effect on the recovery of NDVI. Conversely, severe wetness and either low or high burn severities had a positive effect on recovery. Our study emphasizes the importance of monitoring postfire restoration effects on forest recovery to guide restoration planning and improve forest management in burned areas. This becomes even more relevant under increased wildfire severity predicted for the Mediterranean region interacting with other climate-driven disturbances, which will further negatively affect forest recovery. [ABSTRACT FROM AUTHOR]

Farmers' preferences toward practice‐ and results‐based agri‐environmental schemes (AES) are analysed using a labelled choice experiment. The analysis focuses on schemes involving an innovative satellite‐based monitoring system, with different environmental objectives. Olive groves in southern Spain are used as a case study. Results show no statistically significant differences in farmers' willingness to accept (WTA) payment for participating in practice‐ versus results‐based AES when the scheme targets carbon sequestration. By contrast, farmers require a significantly higher WTA payment for results‐based AES when targeting biodiversity (using bird species as an indicator), mostly due to the uncertainties related to its provision and monitoring. WTA significantly increases with provision level and remote sensing monitoring, regardless of the type of scheme. Significant preference heterogeneity is observed, partly explained by farmers' attitudes toward risk and their beliefs about environmental service provision and monitoring capacity. The results suggest useful policy implications, including the potential of making use of joint provision of environmental services in the design of results‐based AES and accompanying them with uncertainty mitigating measures. [ABSTRACT FROM AUTHOR]

The suitability of halide-based double perovskites for implementation in infrared detectors and thermoelectric devices arises from their inherent environmental stability, non-toxic nature, and demonstrable performance. In the present investigation, our focus centers on an exploration of the structural stability and mechanical attributes intrinsic in Na2CuInY6 (Y = Cl, Br, I) within its cubic phase utilizing DFT. The structural and thermodynamic stability is investigated by computation of tolerance factor and enthalpy of formation. Our methodology encompasses comprehensive calculations of elastic constants based on Born stability criteria that help to understand the mechanical behavior and ductile nature of these compositions. Notably, our scrutiny of the electronic band structure reveals the presence of a direct semiconducting bandgap ranging between 1.30 and 0.36 eV. This distinctive feature holds a pivotal role in facilitating optoelectronic applications because of its pronounced role in absorption within the infrared spectrum. Remarkably, our investigation into the dielectric constant allows us to pinpoint the region of maximal light absorption within the visible spectrum. Lastly, using the BoltzTraP package, we computed the thermoelectric properties of the material and noticed an almost constant value of ZT in the wide range of temperatures highlighting the large range of workability of these compositions for thermoelectric device applications. [ABSTRACT FROM AUTHOR]

Changes in the environmental conditions of Land Use/Land Cover can also significantly influence surface water, mostly due to the dramatically increased biophysical characteristics of the land surfaces. Therefore, extracting multi-scale surface water bodies in urbanized areas is essential. Besides, the past relationships of surface water bodies mostly used low-resolution images. However, the water surface mapping and spatial analysis of multi-scale structure changes in urban areas with high-resolution satellite images have not yet been studied. The present study focused on multi-scale extraction and spatial analysis of growth pattern changes in urban water bodies using Sentinel-2 MSI imagery. Satellite data for the study were obtained from the location map of Chhattisgarh, in the central part of India. The available Sentinel-2 images covering the study area over the period 2012–2020. Initially, we applied image pre-processing steps to remove the shadow noise and distortions and convert the images into a suitable form for mapping. Then, the water surface mapping process combines multi-band water indices (Normalized Difference Vegetation Index and Normalized Difference Water Index (NDWI), Modified NDWI, Urban Difference WI, and Urban Difference Shadow Index and object-oriented methods to extract multi-scale water body information using high-resolution images. Study periods for change analysis were divided into sets. (a) Inter-annual variation is evaluated using the Water Area Frequency Index (WAFI) covering the entire study area over the time period 2012–2020. (b) The spatial variation of land use patterns (i.e., changes in the growth pattern of different scales) in the selected water areas is assessed using eight landscape metrics over three different time periods (2012, 2015, and 2020). These two variations in the WAFI layer are post-processed to determine three multi-scale water scenarios (rivers, streams, canals, and reservoirs): (1) Artificial Waterway (AW of canals, lakes, and reservoirs); (2) Natural Waterway (NW of rivers, streams); and (3) No Waterway (NWW). Two sets of qualitative evaluations are considered: inter-annual variation and spatial variation. The inter-annual variation of surface water areas is evaluated in terms of the WAFI metric percentage. Then the spatial variation of the landscape metrics (Shannon's Diversity Index, Largest Patch Index, Area and Edge metric Percentage, Landscape Division Index, Area-Weighted Mean Shape Index, Aggregation Index, Edge Density, and Patch Density) is analyzed in terms of changes in the selected water areas and changes in the growth pattern for three different time periods. Results and evaluation demonstrate that the accuracy assessment of water mapping methods achieves a high overall accuracy of 95 to 98% for three different time periods. In addition, the observed results of the spatial analysis (AW, NW, and NWW) cover the multi-scale water areas with the highest landscape pattern of fragmentation. Overall, the qualitative findings should therefore be useful for managing and protecting the urban environment. [ABSTRACT FROM AUTHOR]

Timely and accurate estimates of sugarcane yield provide valuable information for food management, bio-energy production, (inter)national trade, industry planning and government policy. Remote sensing and machine learning approaches can improve sugarcane yield estimation. Previous attempts have however often suffered from too few training samples due to the fact that field data collection is expensive and time-consuming. Our study demonstrates that unmanned aerial vehicle (UAV) data can be used to generate field-level yield data using only a limited number of field measurements. Plant height obtained from RGB UAV-images was used to train a model to derive intra-field yield maps based on 41 field sample plots spread over 20 sugarcane fields in the Udon Thani Province, Thailand. The yield maps were subsequently used as reference data to train another model to estimate yield from multi-spectral Sentinel-2 (S2) imagery. The integrated UAV yield and S2 data was found efficient with RMSE of 6.88 t/ha (per 10 m × 10 m pixel), for average yields of about 58 t/ha. The expansion of the sugarcane yield mapping across the entire region of 11,730 km2 was in line with the official statistical yield data and highlighted the high spatial variability of yields, both between and within fields. The presented method is a cost-effective and high-quality yield mapping approach which provides useful information for sustainable sugarcane yield management and decision-making. [ABSTRACT FROM AUTHOR]

The fast and accurate provision of within-season data of green area index (GAI) and total N uptake (total N) is the basis for crop modeling and precision agriculture. However, due to rapid advancements in multispectral sensors and the high sampling effort, there is currently no existing reference work for the calibration of one UAV (unmanned aerial vehicle)-based multispectral sensor to GAI and total N for silage maize, winter barley, winter oilseed rape, and winter wheat. In this paper, a practicable calibration framework is presented. On the basis of a multi-year dataset, crop-specific models are calibrated for the UAV-based estimation of GAI throughout the entire growing season and of total N until flowering. These models demonstrate high accuracies in an independent evaluation over multiple growing seasons and trial sites (mean absolute error of 0.19–0.48 m2 m−2 for GAI and of 0.80–1.21 g m−2 for total N). The calibration of a uniform GAI model does not provide convincing results. Near infrared-based ratios are identified as the most important component for all calibrations. To account for the significant changes in the GAI/ total N ratio during the vegetative phase of winter barley and winter oilseed rape, their calibrations for total N must include a corresponding factor. The effectiveness of the calibrations is demonstrated using three years of data from an extensive field trial. High correlation of the derived total N uptake until flowering and the whole-season radiation uptake with yield data underline the applicability of UAV-based crop monitoring for agricultural applications. [ABSTRACT FROM AUTHOR]

In recent years, computer vision has witnessed significant attention in the research on object detection in remote-sensing images. Unlike objects in traditional natural images, those in remote sensing images are captured vertically by spacecraft, introducing arbitrary directionality, substantial scale variation, and a more complex background. We propose a rotation-equivariant detector enhanced with feature fusion and attention modules to address remote sensing image object detection challenges. Specifically, we introduce a Rotation-Enhanced Feature Extraction (REFE) module and a Rotational Equivariant Attention (REA) module. These enhancements empower the detector to extract object information more effectively from remotely sensed images, filtering out complex background information and improving detection accuracy and stability. Through extensive experiments on diverse and challenging remote sensing image datasets, our method outperforms the task of object detection. Remarkably, our network achieves 1.0, 2.91, and 1.11 mean average precision (mAP) improvements on the DOTA-v1.5, HRSC2016 and DIOR-R datasets. These experimental results robustly demonstrate the effectiveness and superiority of our proposed method. [ABSTRACT FROM AUTHOR]

The intelligent segmentation of high-resolution remote sensing (HRS) image, also called as dense prediction task for HRS image, has been and will continue to be important research in the remote sensing community. In recent years, the growing wave of artificial intelligence (AI) technology has introduced innovative paradigms to this domain, yielding outstanding results and overcoming many challenges with conventional segmentation techniques. This paper provides a comprehensive review of these intelligent segmentation methodologies, including traditional pattern recognition, convolution neural network (CNN)-based, and Transformer-based techniques. However, the explosive but incomplete development of intelligent segmentation techniques also poses more challenges for earth observation experts, the most of which is the technical interpretability. Consequently, we consider these segmentation techniques in the aspect of explainable artificial intelligence (XAI). Data-centric XAI thinks the practical applications of the segmentation model while model-centric XAI will facilitate the understanding of decision-making processes and the adjustment of structural features. Moreover, this review identifies novel research questions and provides constructive insights and recommendations to HRS image segmentation tasks, which may shed new light on the intelligent segmentation methods within the remote sensing image understanding community. [ABSTRACT FROM AUTHOR]

Particulate organic carbon (POC) plays a crucial role in the carbon cycle of inland lake ecosystems. The utilization of remote sensing satellite data provides an effective approach for monitoring the temporal and spatial variations in POC concentration within inland water. However, Erhai Lake, situated in the unique natural environment of the Yunnan-Kweichow Plateau, poses distinct challenges due to the complex and diverse origin of its water quality elements. Existing methods face difficulties in accurately detecting POC concentration in Erhai Lake. In this study, 112 water samples and 574 in-situ remote sensing reflectance curves were collected from Erhai Lake during April, May, and June 2023. The analysis of the optical characteristics of the water in Erhai Lake revealed the closest relationship between the concentration of total particulate matter and POC. Consequently, a POC concentration inversion algorithm was developed, utilizing bands 8, 12, and 16 of Sentinel-3 Ocean and Land Colour Instrument (OLCI). Various POC concentration inversion algorithms were evaluated utilizing a separate dataset. The results indicate that the three-band method offers superior accuracy in POC concentration inversion for Erhai Lake, with a root mean square error (RMSE) of 0.13 mg/L and a mean absolute percentage error (MAPE) of 28.80%. The three-band method was effectively applied to OLCI images from April, May, and June 2023, enabling the analysis of the spatiotemporal distribution of POC in Erhai Lake. [ABSTRACT FROM AUTHOR]

In the context of global carbon emission reduction, solar photovoltaic (PV) technology is experiencing rapid development. Using high-resolution remote sensing images to accurately obtain PV information over a large region, including location and size, has the advantages of high statistical efficiency and timely data update for the PV energy management. Due to the intra-class diversity of PV panels and the intricate variability in their deployment environments, existing semantic segmentation methods often have problems such as under-segmentation and mis-segmentation. To alleviate these problems, this paper proposes an improved DeepLabv3+ semantic segmentation network to more accurately extract PV panels from high-resolution remote sensing images. With the aim of alleviating under-segmentation, a multi-level context aggregation module is developed. This module can enhance the model's ability to learn the characteristics of PV panels and their surrounding environment by aggregating rich contextual information from multi-scale and semantic levels. To alleviate the problem of mis-segmentation, a hybrid attention module is introduced. This module sequentially and adaptively adjusts the weight distribution in both the channel and spatial dimensions, thus enabling the model to focus more on the feature information and spatial positions of PV objects. Experiments conducted on a self-constructed Beijing PV segmentation dataset show that the method in this paper has advantages of completeness and accuracy in extracting PV panels compared to the baseline model and current mainstream semantic segmentation network. In addition, the results of experiments on extracting PV panels in real region show that our model also has good stability and generalization capability. [ABSTRACT FROM AUTHOR]

Because of high-resolution imaging in day and night and any weather condition, Synthetic Aperture Radar (SAR) has various applications in remote sensing. Building detection is one of the important utilization of SAR images. With analysing SAR images information, a new framework based on fusion of statistical, texture, and semantic features is proposed. At first, in order to reduce the speckle noise effects on the classification results, the SAR image is segmented into superpixels which the classification process is performed for these segments. Then, the statistical Fisher and Haralick texture features are extracted and the best features are selected. By applying an adapted VGGNet, the third type of features are extracted. Using training samples, the features achieving the highest classification accuracy are selected and applied to the classifier. Then, the classification output is improved by decreasing the splitting of the large-size buildings and false alarms using morphological operations and contour fitting process. The performance of the proposed framework is evaluated with two different types of TerraSAR-X images of urban areas. Experiment results show that the proposed method has superior results than the similar works. Also, the proposed method has considerable small false alarm rate. [ABSTRACT FROM AUTHOR]

This paper explores, for the first time, a 405 km long wall system located in eastern Mongolia: the "Mongolian Arc" consists of an earthen wall, a trench, and 34 structures. It is part of a much larger system of walls built between the 11th and 13th centuries a.d. The Mongolian Arc, despite its magnitude, has been largely overlooked in existing academic discourse. Our team collected remote sensing data of different types and conducted an archaeological field survey of the entire Mongolian Arc. The different datasets obtained in the lab and the field were analyzed using a geographic information system (GIS). These results were integrated with excerpts from relevant primary sources to provide a preliminary interpretation of the design and potential functions of the Mongolian Arc. Key areas of exploration include the idiosyncratic gaps along the wall, the spatial organization of the wall and structures, and their interrelationship with the adjacent landscape. [ABSTRACT FROM AUTHOR]

Hyper spectral imaging (HSI) is an advanced and fascinating remote sensing method in various domains. Every sample in HS remote sensing images possesses high-size features and has a massive amount of spatial and spectral data that enhances the complexity of feature selection and mining. Also, it improves the interpretational complications and thus surpasses the prediction accuracy of the system. To counterpart such issues, this article introduces an innovative system for HSI categorization wielding introduced Fractional Snake Honey Badger Optimization (FSHBO). Here, image segmentation is done through U-Net, which is trained by Snake Honey Badger Optimization (SHBO). The Deep Belief Network (DBN) is employed for HSI classification that outputs the pixel-wise classified result and this DBN is efficiently tuned using the proposed FSHBO. It is recorded that the proposed FSHBO-DBN has outperformed diverse classical models in terms of accuracy of 0.907, sensitivity of 0.914, and specificity of 0.904. [ABSTRACT FROM AUTHOR]

The most crucial element in accurately monitoring and assessing cotton development is having effective cotton maps. In order to make decisions about governance, precision agriculture, and field management, the county-scale cotton remote sensing categorisation models must be evaluated. The main objective of this research is to propose novel hyperspectral image segmentation approach for cotton crops to monitor the crops and identify early signs of disease. The proposal for a hyperspectral image-based classification of cotton crops is made in this research. Using 'Modified Hierarchical density-based spatial clustering of applications with noise (HDBSCAN),' the procedure begins with the input image being segmented. Following this, features based on vegetation indices, hybrid vegetation indices, and statistical characteristics will be retrieved and trained with the classification model to ensure proper classification. Specifically, EVI, NDVI, and RVI are features that are based on vegetation indices. Using techniques like SVM, CNN, DBN, DT, and Improved Bidirectional Long Short-Term Memory (IBi-LSTM), this study replicates a stacked ensemble framework for classification. While the MHDBSCAN achieved the maximum accuracy value of 97.97%, the conventional techniques achieved limited accuracy. Thus, the MHDBSCAN far more effective at classifying the crop utilising hyperspectral image segmentation and the classification become more precise and accurate. [ABSTRACT FROM AUTHOR]

Hyperspectral anomaly detection can separate sparse anomalies from the low-rank background component under an unsupervised behavior due to sufficient spectral information. Therefore, hyperspectral image anomaly detection technology has great application potential and value in public security and national defense. Currently, most existing models attempt to detect anomalous targets with a sparsity prior, without further considering the visual saliency of the targets themselves. To tackle this issue, this paper proposes a saliency-guided sparse low-rank tensor approximation model, called SSLR, to detect anomalous targets from hyperspectral remote sensing images in an unsupervised manner. Specifically, we first explore the saliency information of each pixel for regularizing the sparse anomaly matrix. We then suggest a three-directional tensor nuclear norm to obtain a low-rank background to characterize the background component. We solve the SSLR optimization problem by an efficient alternating direction method of multipliers framework. Experiments conducted on benchmark hyperspectral datasets demonstrate that the proposed SSLR outperforms some state-of-the-art anomaly detection methods. [ABSTRACT FROM AUTHOR]

Primates are adept at dealing with fluctuating availability of resources and display a range of responses to minimize the effects of food scarcity. An important component of primate conservation is to understand how primates adapt their foraging and ranging patterns in response to fluctuating food resources. Animals optimize resource acquisition within the home range through the selection of resource‐bearing patches and choose between contrasting foraging strategies (resource‐maximizing vs. area‐minimizing). Our study aimed to characterize the foraging strategy of a folivorous primate, Verreaux's sifaka (Propithecus verreauxi), by evaluating whether group home range size varied between peak and lean leaf seasons within a seasonally dry tropical forest in Madagascar. We hypothesized that Verreaux's sifaka used the resource maximization strategy to select high‐value resource patches so that during periods of resource depression, the home range area did not significantly change in size. We characterized resource availability (i.e., primary productivity) by season at Kirindy Mitea National Park using remotely‐sensed Enhanced Vegetation Index data. We calculated group home ranges using 10 years of focal animal sampling data collected on eight groups using both 95% and 50% kernel density estimation. We used area accumulation curves to ensure each group had an adequate number of locations to reach seasonal home range asymptotes. Neither 95% home ranges nor 50% core areas differed across peak and lean leaf resource seasons, supporting the hypothesis that Verreaux's sifaka use a resource maximization strategy. With a better understanding of animal space use strategies, managers can model anticipated changes under environmental and/or anthropogenic resource depression scenarios. These findings demonstrate the value of long‐term data for characterizing and understanding foraging and ranging patterns. We also illustrate the benefits of using satellite data for characterizing food resources for folivorous primates. Research Highlights: While seasonal leaf availability (characterized using Enhanced Vegetation Index) differed between peak and lean leaf seasons, we found no significant variation in home range and core area sizes of Verreaux's sifaka groups at Kirindy Mitea National Park, Madagascar.Our findings suggest Verreaux's sifaka use a resource‐maximizing strategy.Home range area estimates are improved when an asymptote analysis is used to ensure an adequate number of location samples and when temporal requirements are imposed to avoid concentrated sampling. [ABSTRACT FROM AUTHOR]

This study aims to develop an automated impact crater classification machine learning (ML) method based on the morphometric parameters extracted from SRTM DEM. The training and testing dataset comprises data from 52 confirmed, well preserved, and moderately eroded impact craters and a recently discovered impact crater in Korea, Jeokjung Chogye Basin (JCB). The morphometric parameters including rim diameter, floor diameter, and wall width of complex craters and simple craters were tested by Mann Whitney U test and One Sample Wilcoxon signed rank test. The tests showed that those parameters can statistically separate the two types of craters. The Random Forest model classified them with an accuracy of 88.6% and a Kappa coefficient of 0.67, where rim diameter, floor diameter, and wall width were identified as variables with the highest Gini indices. Complex craters are characterized by a large flat diameter and wide wall width compared to simple craters with parabolic bases. The difference is caused by the impact energy when the craters were formed. The study confirmed that using machine learning, the complex craters and simple craters can be separated by checking the SRTM elevation model with machine learning methods. The morphometric parameters of JCB impact crater indicated that the crater is highly a complex crater concluded by both statistical tests and machine learning algorithm. [ABSTRACT FROM AUTHOR]

Hyperspectral data has a significant count of spectral channels with an enhanced spectral resolution, which provides detailed information at each pixel. This data can be used in numerous remote sensing (RS) applications, along with mineral mapping. Mineral mapping is an important component of geological mapping, which helps in investigating the mineralization potential of an area. This work can be completed effectively by applying machine learning (ML) techniques to RS data. This paper proposes a stacked ensemble-based framework for mineral mapping using the dataset obtained by the Airborne Visible Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG). The study area is situated in Jahazpur, Rajasthan, India. The purpose of this stacked ensemble-based model is to enhance the performance of ML-based mineral mapping. The proposed stacked ensemble model consists of two major elements: a base learner (Naïve Bayes, KNN, artificial neural network, decision tree, and support vector machine) and a stacked learner (random forest). The results of the experiments show that the stacked ensemble-based model has a lot of potential for accurately mapping the minerals talc, montmorillonite, kaolionite, and kaosmec. The proposed model has obtained an overall accuracy of 98.96%, an average accuracy of 98.21%, and a Kappa coefficient of 0.9628. Research highlights: A stacked ensemble-based model for mineral mapping is proposed. The well-known five conventional machine learning models (called base models) are investigated for mineral mapping. The performance of the proposed model is evaluated on the AVIRIG–NG dataset. The study area is situated in Jahazpur, Rajasthan, India. The proposed method outperformed all base models. [ABSTRACT FROM AUTHOR]

In the current era, remote sensing is a powerful platform for detecting and predicting landslides. Moreover, the advancement in computing technologies has proven significant in artificial intelligence (AI) research. Researchers have made significant attempts in the existing literature by introducing landslide detection procedures from remote sensing images (RSIs) through deep learning (DpLr) algorithms. This research work aims to survey those methods. Our database consists of 204 published research articles. In addition, 50% (approximately) of the papers are directly related to landslide information extraction from satellite and unmanned aerial vehicles (UAV) images exploiting DpLr models. The suggested methods have been categorized into seven parts based on the applied model. Further, the evaluation methods have been discussed. The quantitative results are based on the following parameters: (1) contributing nations, (2) key study locations, (3) data set distribution, and (4) model utilization. Lastly, challenges in the studies of DpLr algorithms and the opportunities in landslide detection problems are discussed to motivate future research. [ABSTRACT FROM AUTHOR]

Himalayan glaciers have shown a retreating trend since the Little Ice Age (LIA) in response to climate change. As glaciers are crucial for water security and ecological sustainability, it becomes necessary to map and monitor the glacial status from time to time. The present study is focused on the study of Haptal glacier located in the Bhuzas sub-basin of Kishtwar district of Jammu and Kashmir (UT), India, between the Pir-Panjal and Greater Himalayan range using satellite data. Results revealed that the glacier retreated continuously at progressive rates between 1980 and 2020, with an annual retreat rate of 28.25 ± 1.85 m a−1. During 1999–2009, the highest (67.93 ± 2.8 m a−1) retreat rate was observed. Maximum surface velocity was estimated during 1999–2000 (38.5 ± 4.7 m a−1), while the glacier experienced the minimum surface velocity during 2019–2020 (32.5 ± 3.7 m a−1). The glacier has lost its area (22.60 ± 8.18%), glacial length (10.95 ± 0.7%), and glacier ice volume (1.47 ± 0.56 km3; 29.63 ± 11.47%) during the study period. Modelled mean ice thickness using Glabtop2 for the glacier is estimated at 129.28 ± 13 m. The accumulation area values showed a decreasing trend of 10.89 ± 0.56 km2 to 8.15 ± 0.3 km2, indicating a change of 25.05 ± 5.8% between 1999 and 2020. Upward migration of snow line altitude from 5148 m (1999) to 5198 m (2020) indicates enhanced melting and glacier loss during the study period. The study further revealed that there is an overall decreasing trend in specific mass balance. Research highlights: Haptal glacier retreated at progressive rates between 1980 and 2020 The rate of the recession was higher during 1999–2009 The upward migration of SLA showed melting process during the study period Surface ice velocity of glacier is reduced during 1999–2021. Temperature shows increasing trend and precipitation shows decreasing trend. [ABSTRACT FROM AUTHOR]

Koh-i-Noor and other world-famous diamonds such as Hope, Orloff, Great Mogul, Nizam, and Pitt, well-known in the industry as 'Golkonda Diamonds' are very well recognised for their rare colours, large carat sizes, and because of the paucity of nitrogen atoms majority of them have been classified as Type IIa diamonds. These renowned Golkonda diamonds were recovered from placers mined on the banks of the Krishna River in southern India; however, their primary source rocks (either kimberlites or lamproites) remain questioned and untraced. Precise identification of the primary sources of such large-sized, dominantly Type IIa diamonds (i.e., CLIPPIRS) is crucial for understanding their deep mantle origin, nature and timing of magmatism carrying them and essential from economic and geological perspectives. We employed a multidisciplinary approach incorporating xenocrystic mineral composition and bulk-rock geochemistry, field geological and remote sensing (GIS) studies to locate the probable primary sources of these renowned diamonds, know the origin of Type IIa Golkonda diamonds in southern India, and to understand the mechanism and timing of diamond transport and dispersal as placers in the Krishna River basin. Our study rules out the possibility of various lamproite occurrences of the Eastern Dharwar Craton and Banganapalle conglomerates as being sources of Koh-i-Noor and other Golkonda diamonds. The absence of Type IIa diamonds in the highly diamondiferous Late Cretaceous kimberlites of Wajrakarur likewise excludes them as source of Golkonda diamonds. Among southern India's two significant kimberlite fields, i.e., Wajrakarur and Narayanpet, compositions of indicator minerals from the Wajrakarur Kimberlite Field (WKF) reveal their ultimate diamond preservation potential, presence of strong diamondiferous mantle roots and deeper source regions, hence recognising them to be the potential sources of Golkonda diamonds. GIS and remote sensing tools were used to calculate moisture content, vegetation indices, and to locate paleo-channel of the Penner River, which was primarily responsible for the transportation of diamonds from their Mesoproterozoic (ca. 1.1 Ga) source rocks at Wajrakarur to their final sites of recovery, i.e., Kolluru and other mines situated on the banks of the Krishna River. The occurrence of alluvial placer deposits in Krishna River drainage system is analogous to the Orange River drainage system in South Africa. Both areas have diamonds sourced from primary kimberlite pipes, transported by rivers, and deposited in specific areas. Similarities in the origin, mechanism of diamond transport, dispersal and deposition have played a crucial role in significant diamond production from alluvial deposits in Krishna and Orange Rivers. [ABSTRACT FROM AUTHOR]

The Wikki Warm Spring is one of the promising locations for the development of geothermal projects in Nigeria. Radiometric and remote sensing data were interpreted to enhance the understanding of the factors controlling the geothermal energy sources in the Wikki Warm Spring. Thus, mapping locations of concealed heat sources offer concentration areas for follow-up geothermal exploration. Landsat-8 imagery was used to produce the land surface temperature (LST) map, which reveals surface temperature variation that ranges from 50 to 95 °C. In comparison, the radiogenic heat map of the region generated from the radiometric data of the study area shows radiogenic heat production rate, which ranged from less than 0.69 to above 3.91 µWm−3. The radiogenic heat and LST maps show similar features, indicating that Basement Complex terrain exhibits high radiogenic and surface temperature than the Benue Trough. Monte Carlo simulation reveals statistical values that suggest that the most likely radiogenic heat value is 1.95 µWm−3 around the warm spring, the highest possible (best case scenario) heat value is 2.23 µWm−3, and the least possible value (worst case scenario) is 1.69 µWm−3. The Basement Complex terrain northwest of the warm spring produced high radiogenic heat, generating values above 3.91 μWm−3. The outcome of this investigation is very important for explorationists to institute sustainable geothermal energy mitigation plans and produce a clean and renewable energy in Wikki Warm Spring. [ABSTRACT FROM AUTHOR]

Brief introduction: What are microclimates and why are they important? Microclimate science has developed into a global discipline. Microclimate science is increasingly used to understand and mitigate climate and biodiversity shifts. Here, we provide an overview of the current status of microclimate ecology and biogeography in terrestrial ecosystems, and where this field is heading next. Microclimate investigations in ecology and biogeography: We highlight the latest research on interactions between microclimates and organisms, including how microclimates influence individuals, and through them populations, communities and entire ecosystems and their processes. We also briefly discuss recent research on how organisms shape microclimates from the tropics to the poles. Microclimate applications in ecosystem management: Microclimates are also important in ecosystem management under climate change. We showcase new research in microclimate management with examples from biodiversity conservation, forestry and urban ecology. We discuss the importance of microrefugia in conservation and how to promote microclimate heterogeneity. Methods for microclimate science: We showcase the recent advances in data acquisition, such as novel field sensors and remote sensing methods. We discuss microclimate modelling, mapping and data processing, including accessibility of modelling tools, advantages of mechanistic and statistical modelling and solutions for computational challenges that have pushed the state‐of‐the‐art of the field. What's next?: We identify major knowledge gaps that need to be filled for further advancing microclimate investigations, applications and methods. These gaps include spatiotemporal scaling of microclimate data, mismatches between macroclimate and microclimate in predicting responses of organisms to climate change, and the need for more evidence on the outcomes of microclimate management. [ABSTRACT FROM AUTHOR]

Morphometry is the process that deals with mathematical analysis and calculations of the various land surface dimensions. In this study, morphometry analysis and changes in riverbeds due to anthropogenic activities have been studied using geospatial techniques for a stretch of the Yamuna river in Delhi. The parametric values related to morphometry, such as low permeability and high surface run-off were determined through Remote Sensing, which is helpful to understand the characteristics of the area. The study reveals that morphometric parameters and land surface properties are closely interrelated and are dependent on each other. Analysis has lightened up that over the year river span has been reduced from 5.15 to 4.23 sq. km and there is a trend of reduction and alteration of the channel in upcoming days. The morphometric conditions also indicate a concern of flood during monsoon. This study also focuses on the adverse effects of anthropogenic activities on the Yamuna riverbed morphology. There is a need for restriction on haphazard human activities, effective planning and management for sustainable development of the Yamuna riverbed in Delhi. The study suggests further research on aquatic ecology, water quality, and life expectancy of the river due to immense anthropogenic pressure. [ABSTRACT FROM AUTHOR]

The Himalayan region is the most sensitive due to its fragility, especially in soil erosion; therefore, it is a growing concern for environmentalists and natural resource planners. The study river basin Mandakini is situated in the central part of the Garhwal Himalayan region (Uttarakhand, India), which is highly prone to soil erosion due to various hydro-geomorphological factors. The factors include precipitous slope, geology, rugged terrain, land use and drainage pattern. Therefore, to identify the erosion-prone areas of the study basin, employed watershed prioritization technique using geographical information system and remote sensing integrated with weighted sum analysis (WSA), sediment production rate (SPR) and Technique of Order Preference Similarity to the Ideal Solution with Analytical Hierarchical Process (AHP-TOPSIS) models. It is calculated by taking different parameters indicating linear, landscape, and shape parameters. All the sub-watersheds (SW) of the basin were prioritized in different categories for all models with model performance for the Mandakini river basin in the central Himalaya. The results are showing almost similar results except for high erosion-prone regions. The results of the SPR model indicate that vary large areas (43.47%) of the basin suffering from severe erosion limited in the north-central (WS11, WS12, WS21), eastern (WS2), and southern (WS22 and WS23) parts of the basin among 23 sub-watersheds. The result of model evaluation indicates AHP-TOPSIS is the efficient model in assessing soil erodibility. The study can help to undertake the precise decisions to propose an effective framework for soil erosion control measures and encourage soil conservation priorities of the region. The findings have implications for defining sustainable land resource management and conservation, which are critical to attaining the United Nations' 2030 Agenda for Sustainable Development's societal goals. [ABSTRACT FROM AUTHOR]

The classification of hyperspectral images (HSI) into categories that correlate to various land cover sorts such as water bodies, agriculture and urban areas, has gained significant attention in research due to its wide range of applications in fields, such as remote sensing, computer vision, and more. Supervised deep learning networks have demonstrated exceptional performance in HSI classification, capitalizing on their capacity for end-to-end optimization and leveraging their strong potential for nonlinear modeling. However, labelling HSIs, on the other hand, necessitates extensive domain knowledge and is a time-consuming and labour-intensive exercise. To address this issue, the proposed work introduces a novel semi-supervised network constructed with an autoencoder, Siamese action, and attention layers that achieves excellent classification accuracy with labelled limited samples. The proposed convolutional autoencoder is trained using the mass amount of unlabelled data to learn the refinement representation referred to as 3D-CAE. The added Siamese network improves the feature separability between different categories and attention layers improve classification by focusing on discriminative information and neglecting the unimportant bands. The efficacy of the proposed model's performance was assessed by training and testing on both same-domain as well as cross-domain data and found to achieve 91.3 and 93.6 for Indian Pines and Salinas, respectively. [ABSTRACT FROM AUTHOR]

Background: Stingless bees are vital pollinators and honey producers in the tropics. Research on stingless bees is generally underrepresented compared to the western honeybees, and while stingless bee studies from some regions are reported, there is a particular lack of reports on the species endemic to Sub-Saharan Africa. Since conventional entomological methods such as mark-recapture and radar harmonic tags suffer from limited observation counts and amount to a significant payload, fluorescent powder tagging offers a promising alternative to understanding their behavior. We deploy a hyperspectral fluorescence lidar monitors a 25-mm-wide transect in front of the hives. Results: During a 1 day study at the International Stingless Bee Center, near Kakum National Park, Ghana, 17,862 insects were observed with the lidar, of which 7520 were tagged with fluorescent dyes. Approximately half of the bees from the selected hives were successfully tagged, with an estimated misclassification of 1%. According to our limited data, the observed species, Meliponula bocandei and the Dactylurina staudingeri exhibited different activity patterns. D. staudingeri displayed a half-hour longer active day, with clear crepuscular activity peaks. In contrast, M. bocandei activity was diurnal, with less pronounced crepuscular peaks. Conclusions: We demonstrate how hyperspectral fluorescence lidar can monitor powder-tagged insects throughout the day. The monitored species revealed distinct activity patterns over the day. Our findings highlight the potential of this technology as a valuable tool for understanding insect behavior and environmental preferences of species, in situ, which could potentially give clues of response to climate changes of these critical species. [ABSTRACT FROM AUTHOR]

Global warming has intensified the intensity of compound drought‐hot extremes (CDHEs), posing more severe impacts on human societies and ecosystems than individual extremes. The vulnerability of global terrestrial ecosystems under CDHEs, along with its key influencing factors, remains poorly understood. Based on multiple remote sensing data, we construct a Vine Copula model to appraise vegetation vulnerability under CDHEs, and attribute it to climatic and biotic factors for five different vegetation types. High vulnerability is detected in central and southern regions of North America, eastern and southern regions of South America, Southern Africa, northern and western Europe, and northern and eastern Australia. The drier the climate, the higher will be the vulnerability. Furthermore, biodiversity and biomass are key biotic factors influencing the vulnerability of various vegetation types, such that ecosystems with richer biodiversity and higher biomass have lower vulnerability to CDHEs. The findings deepen understanding of terrestrial ecosystem response to CDHEs. Plain Language Summary: Drought and hot‐related extremes often coincide or follow one another, known as compound drought‐hot extremes (CDHEs), adversely affecting various vegetation processes. Thus, investigating the response relationship between vegetation dynamics and CDHEs is critical for maintaining the sustainable development of ecosystems under the background of climate warming. High ecosystem vulnerability is detected in central and southern regions of North America, eastern and southern regions of South America, Southern Africa, northern and western Europe, and northern and eastern Australia. Climatic factors (precipitation, arid index, temperature, and radiation) dominate the vulnerability of all vegetation types. The drier the climate, the higher will be the vulnerability of vegetation to CDHEs. Furthermore, biodiversity and biomass are key biotic factors influencing the vulnerability. The results provide us with essential insights for managing and adapting terrestrial ecosystems against climate change and are of interest to a wide range of audiences, including but not limited to ecologists, hydrologists, and climatologists. Key Points: A framework is developed to estimate the vegetation vulnerability in response to compound drought‐hot extremes and attribute it to various factorsVegetation vulnerability is higher for grasses and shrubs than for evergreen and deciduous forestsVegetation vulnerability is both affected by climate and biotic factors, but climate factors are more dominant [ABSTRACT FROM AUTHOR]

Anthropogenic activity drives extensive tropical deforestation, particularly in Southeast Asia where 16% of total forest cover was lost between 2000 and 2020. While land surface changes significantly affect the atmosphere, their net impact on convective clouds is not well‐constrained. Here, we use satellite data to demonstrate long‐term deforestation in Southeast Asia robustly alters cloud properties and provide the first observational evidence that the magnitude of this response depends on the atmospheric environment. Deforestation drives a shift toward more widespread, shallower clouds during the daytime, with amplified effects in dry inland areas compared with moist coastal regions. Aerosols only weakly modulate the cloud fraction response, but offset the cloud top height response to deforestation, suggesting the influence of aerosol indirect effects. We conclude that the local signature of forest loss is not uniform, and regional differences in climatology must be considered when assessing deforestation impacts on clouds and the climate system. Plain Language Summary: Humans are driving widespread deforestation in the tropics. Changes to the land surface following forest loss are generally known to affect the atmosphere, but it is hard to tell how deforestation will impact clouds in a given area. Here, we focus on Southeast Asia, a region of the world facing dramatic large‐scale deforestation. We use two decades of satellite data to estimate how the loss of tropical forests impacts cloud properties. On average, we find that deforestation leads to more widespread and shallower clouds. We then look further into how this cloud response to deforestation depends on other environmental factors like moisture and aerosols. This gives us a better idea of which regions are most sensitive to changes in forest cover. Overall, our results show there is an observable cloud response to deforestation, but this response may be stronger in some regions than in others depending on underlying moisture and aerosol conditions. As forest loss continues in Southeast Asia and across the world, it is important to further study these region‐dependent interactions between the atmosphere and the land surface so we can better understand the impacts of human‐driven deforestation on weather and climate. Key Points: Deforestation in Southeast Asia drives a robust shift toward more widespread and shallower clouds on an annual timescaleThis effect has been debated in modeling studies, but we demonstrate this observationally using two decades of satellite dataSome regions are especially vulnerable to deforestation‐driven changes in clouds, depending on atmospheric moisture and aerosol loading [ABSTRACT FROM AUTHOR]

The synergy between artificial intelligence (AI) and agricultural sciences has garnered substantial attention, especially in the realm of crop yield prediction. The present bibliometric analysis examines the worldwide research trends about the application of AI in predicting crop yields. The global literature on crop yield prediction using AI published between 1997 and 2022 is searched in the Scopus database. Five hundred and forty research articles were used to compile the analysis; they were located in the Scopus database and processed through the VOSviewer. Our research reveals a significant surge in scholarly publications, particularly focusing on countries including China, the United States, India and Canada. These research endeavours aim to apply AI methodologies for forecasting agricultural produce yields in tandem with developments in remote sensing technologies that facilitate more accurate yield predictions. These insights offer a valuable reference for researchers and illuminate potential directions for future investigations in the domain of AI-based crop yield prediction. [ABSTRACT FROM AUTHOR]

Culicoides imicola is the main vector of viral diseases of livestock in Europe such as bluetongue (BT), African horse sickness and epizootic haemorrhagic disease. Climatic factors are the main drivers of C. imicola occurrence and its distribution might be subject to rapid shifts due to climate change. Entomological data, collected during BT surveillance, and climatic/environmental variables were used to analyse ecological niche and to model C. imicola distribution and possible future range shifts in Italy. An ensemble technique was used to weigh the performance of machine learning, linear and profile methods. Updated future climate projections from the latest phase of the Climate Model Intercomparison Project were used to generate future distributions for the next three 20‐year periods, according to combinations of general circulation models and shared socioeconomic pathways and considering different climate change scenarios. Results indicated the minimum temperature of the coldest month (BIO 6) and precipitation of the driest‐warmest months (BIO 14) as the main limiting climatic factors. Indeed, BIO 6 and BIO 14 reported the two highest values of variable importance, respectively, 9.16% (confidence interval [CI] = 7.99%–10.32%), and 2.01% (CI = 1.57%–2.44%). Under the worst‐case scenario of climate change, C. imicola range is expected to expand northward and shift away from the coasts of central Italy, while in some areas of southern Italy, environmental suitability will decrease. Our results provide predictions of C. imicola distribution according to the most up‐to‐date future climate projections and should be of great use to surveillance management at regional and national scales. [ABSTRACT FROM AUTHOR]