Search

Animals disperse seeds in various ways that affect seed deposition sites and seed survival, ultimately shaping plant species distribution, community composition, and ecosystem structure. Some animal species can disperse seeds through multiple pathways (e.g., defecation, regurgitation, epizoochory), each likely producing distinct seed dispersal outcomes. We studied how seed traits (size and toughness) interact with disperser species to influence seed dispersal pathway and how this ultimately shapes the proportion of seeds deposited in various habitat types. We focused on three frugivorous species of duikers (African forest antelopes) in the Dja Faunal Reserve, a tropical rainforest in southern Cameroon. Duikers can both defecate and regurgitate seeds, the latter predominantly occurring during rumination at their bedding sites (or "nests"). We located duiker nests and dungs along 18 linear 1-km-transects to assess: (1) how seed traits affect the likelihood of dispersal via defecation versus regurgitation, (2) if defecated versus regurgitated seeds are deposited at different rates in different forest types (assessed by indigenous Baka), microhabitats, and forest structural attributes (measured by drone lidar), and (3) if these differ between three duiker species that vary in size and diel activity patterns. We found that duikers predominantly defecated small seeds (10 mm length), the latter including 25 different plant species. The three duiker species varied in their nesting habits, with nocturnal bay duikers (Cephalophus dorsalis) nesting in dense understory vegetation at proportions 3-4 times higher than Peter's and yellow-backed duikers (Cephalophus callipygus and Cephalophus silvicultor). As a result, bay duikers deposited larger regurgitated seeds at a higher rate in habitats with denser understory where lianas and palms predominate and near fallen trees. This directed regurgitation seed deposition likely plays an important and unique role in forest succession and structure. This study highlights the importance of ungulate seed dispersal by regurgitation, a vastly understudied process that could impact many ecosystems given the prevalence of ruminating ungulates worldwide.

Solar-induced fluorescence (SIF) is a proxy of ecosystem photosynthesis that often scales linearly with gross primary productivity (GPP) at the canopy scale. However, the mechanistic relationship between GPP and SIF is still uncertain, especially at smaller temporal and spatial scales. We deployed a ultra-hyperspectral imager over two grassland sites in California throughout a soil moisture dry down. The imager has high spatial resolution that limits mixed pixels, enabling differentiation between plants and leaves within one scene. We find that imager SIF correlates well with diurnal changes in leaf-level physiology and gross primary productivity under well-watered conditions. These relationships deteriorate throughout the dry down event. Our results demonstrate an advancement in SIF imaging with new possibilities in remotely sensing plant canopies from the leaf to the ecosystem. These data can be used to resolve outstanding questions regarding SIF's meaning and usefulness in terrestrial ecosystem monitoring.

The intensifying global opioid crisis, majorly attributed to fentanyl (FT) and its analogs, has necessitated the development of rapid and ultrasensitive remote/on-site FT sensing modalities. However, current approaches for tracking FT exposure through wastewater-based epidemiology (WBE) are unadaptable, time-consuming, and require trained professionals. Toward developing an extended in situ wastewater opioid monitoring system, we have developed a screen-printed electrochemical FT sensor and integrated it with a customized submersible remote sensing probe. The sensor composition and design have been optimized to address the challenges for extended in situ FT monitoring. Specifically, ZIF-8 metal-organic framework (MOF)-derived mesoporous carbon (MPC) nanoparticles (NPs) are incorporated in the screen-printed carbon electrode (SPCE) transducer to improve FT accumulation and its electrocatalytic oxidation. A rapid (10 s) and sensitive square wave voltammetric (SWV) FT detection down to 9.9 µgL-1 is thus achieved in aqueous buffer solution. A protective mixed-matrix membrane (MMM) has been optimized as the anti-fouling sensor coating to mitigate electrode passivation by FT oxidation products and enable long-term, intermittent FT monitoring. The unique MMM, comprising an insulating polyvinyl chloride (PVC) matrix and carboxyl-functionalized multi-walled carbon nanotubes (CNT-COOH) as semiconductive fillers, yielded highly stable FT sensor operation (> 95% normalized response) up to 10 h in domestic wastewater, and up to 4 h in untreated river water. This sensing platform enables wireless data acquisition on a smartphone via Bluetooth. Such effective remote operation of submersible opioid sensing probes could enable stricter surveillance of community water systems toward timely alerts, countermeasures, and legal enforcement.

Abstract: Quantifying evapotranspiration (ET) is critical to accurately predict vegetation health, groundwater recharge, and streamflow generation. Hillslope aspect, the direction a hillslope faces, results in variable incoming solar radiation and subsequent vegetation water use that drive ET. Previous work in watersheds with a single dominant vegetation type (e.g., trees) have shown that equator‐facing slopes (EFS) have higher ET compared to pole‐facing slopes (PFS) due to higher evaporative demand. However, it remains unclear how differences in vegetation type (i.e., grasses and trees) influence ET and water partitioning between hillslopes with opposing aspects. Here, we quantified ET and root‐zone water storage deficits between a PFS and EFS with contrasting vegetation types within central coastal California. Our results suggest that the cooler PFS with oak trees has higher ET than the warmer EFS with grasses, which is counter to previous work in landscapes with a singule dominant vegetation type. Our root‐zone water storage deficit calculations indicate that the PFS has a higher subsurface storage deficit and a larger seasonal dry down than the EFS. This aspect difference in subsurface water storage deficits may influence the subsequent replenishment of dynamic water storage, groundwater recharge and streamflow generation. In addition, larger subsurface water deficits on PFS may reduce their ability to serve as hydrologic refugia for oaks during multi‐year droughts. This research provides a novel integration of field‐based and remotely‐sensed estimates of ET required to properly quantify hillslope‐scale water balances. These findings emphasize the importance of resolving hillslope‐scale vegetation structure within Earth system models, especially in landscapes with diverse vegetation types.

Methane is a major contributor to anthropogenic greenhouse gas emissions. Identifying large sources of methane, particularly from the oil and gas sectors, will be essential for mitigating climate change. Aircraft-based methane sensing platforms can rapidly detect and quantify methane point-source emissions across large geographic regions, and play an increasingly important role in industrial methane management and greenhouse gas inventory. We independently evaluate the performance of five major methane-sensing aircraft platforms: Carbon Mapper, GHGSat-AV, Insight M, MethaneAIR, and Scientific Aviation. Over a 6 week period, we released metered gas for over 700 single-blind measurements across all five platforms to evaluate their ability to detect and quantify emissions that range from 1 to over 1,500 kg(CH4)/h. Aircraft consistently quantified releases above 10 kg(CH4)/h, and GHGSat-AV and Insight M detected emissions below 5 kg(CH4)/h. Fully blinded quantification estimates for platforms using downward-facing imaging spectrometers have parity slopes ranging from 0.76 to 1.13, with R2 values of 0.61 to 0.93; the platform using continuous air sampling has a parity slope of 0.5 (R2 = 0.93). Results demonstrate that aircraft-based methane sensing has matured since previous studies and is ready for an increasingly important role in environmental policy and regulation.

Coastal terrestrial-aquatic interfaces (TAIs) are crucial contributors to global biogeochemical cycles and carbon exchange. The soil carbon dioxide (CO2) efflux in these transition zones is however poorly understood due to the high spatiotemporal dynamics of TAIs, as various sub-ecosystems in this region are compressed and expanded by complex influences of tides, changes in river levels, climate, and land use. We focus on the Chesapeake Bay region to (i) investigate the spatial heterogeneity of the coastal ecosystem and identify spatial zones with similar environmental characteristics based on the spatial data layers, including vegetation phenology, climate, landcover, diversity, topography, soil property, and relative tidal elevation; (ii) understand the primary driving factors affecting soil respiration within sub-ecosystems of the coastal ecosystem. Specifically, we employed hierarchical clustering analysis to identify spatial regions with distinct environmental characteristics, followed by the determination of main driving factors using Random Forest regression and SHapley Additive exPlanations. Maximum and minimum temperature are the main drivers common to all sub-ecosystems, while each region also has additional unique major drivers that differentiate them from one another. Precipitation exerts an influence on vegetated lands, while soil pH value holds importance specifically in forested lands. In croplands characterized by high clay content and low sand content, the significant role is attributed to bulk density. Wetlands demonstrate the importance of both elevation and sand content, with clay content being more relevant in non-inundated wetlands than in inundated wetlands. The topographic wetness index significantly contributes to the mixed vegetation areas, including shrub, grass, pasture, and forest. Additionally, our research reveals that dense vegetation land covers and urban/developed areas exhibit distinct soil property drivers. Overall, our research demonstrates an efficient method of employing various open-source remote sensing and GIS datasets to comprehend the spatial variability and soil respiration mechanisms in coastal TAI. There is no one-size-fits-all approach to modeling carbon fluxes released by soil respiration in coastal TAIs, and our study highlights the importance of further research and monitoring practices to improve our understanding of carbon dynamics and promote the sustainable management of coastal TAIs.

With increased interest in forest restoration comes an urgent need to provide accurate, scalable, and cost‐effective monitoring tools. The ubiquity of smartphones has led to a surge in monitoring apps. We reviewed and assessed monitoring apps found through web searches and conversations with practitioners. We identified 42 apps that (1) automatically monitor indicators or (2) facilitate data entry. We selected the five most promising from the first category, based on their relevance, availability, stability, and user support. We compared them to traditional field techniques in a well‐studied restoration project in Costa Rica. We received further feedback from 15 collaborator organizations that evaluated these in their corresponding field restoration sites. Diameter measurements correlated well with traditional tape‐based measurements (R2 = 0.86–0.89). Canopy openness and ground cover showed weaker correlations to densiometer and quadrat cover measurements (R2 = 0.42–0.51). Apps did not improve labor efficiency but do preclude the purchase of specialized field equipment. The apps reviewed here need further development and validation to support monitoring adequately, especially in the tropics. Estimates of development and maintenance costs, as well as statistics on user uptake, are required for cost‐effective development. We recommend a coordinated effort to develop dedicated restoration monitoring apps that can speed up and standardize the collection of indicators and provide evidence on restoration outcomes alongside a centralized repository of this information.

Estimates of the land area occupied by wind energy differ by orders of magnitude due to data scarcity and inconsistent methodology. We developed a method that combines machine learning-based imagery analysis and geographic information systems and examined the land area of 318 wind farms (15,871 turbines) in the U.S. portion of the Western Interconnection. We found that prior land use and human modification in the project area are critical for land-use efficiency and land transformation of wind projects. Projects developed in areas with little human modification have a land-use efficiency of 63.8 ± 8.9 W/m2 (mean ±95% confidence interval) and a land transformation of 0.24 ± 0.07 m2/MWh, while values for projects in areas with high human modification are 447 ± 49.4 W/m2 and 0.05 ± 0.01 m2/MWh, respectively. We show that land resources for wind can be quantified consistently with our replicable method, a method that obviates >99% of the workload using machine learning. To quantify the peripheral impact of a turbine, buffered geometry can be used as a proxy for measuring land resources and metrics when a large enough impact radius is assumed (e.g., >4 times the rotor diameter). Our analysis provides a necessary first step toward regionalized impact assessment and improved comparisons of energy alternatives.

Cyanobacterial harmful algal blooms (cyanoHABs) can harm people, animals, and affect consumptive and recreational use of inland waters. Monitoring cyanoHABs is often limited. However, chlorophyll-a (chl-a) is a common water quality metric and has been shown to have a relationship with cyanobacteria. The World Health Organization (WHO) recently updated their previous 1999 cyanoHAB guidance values (GVs) to be more practical by basing the GVs on chl-a concentration rather than cyanobacterial counts. This creates an opportunity for widespread cyanoHAB monitoring based on chl-a proxies, with satellite remote sensing (SRS) being a potentially powerful tool. We used Sentinel-2 (S2) and Sentinel-3 (S3) to map chl-a and cyanobacteria, respectively, classified chl-a values according to WHO GVs, and then compared them to cyanotoxin advisories issued by the California Department of Water Resources (DWR) at San Luis Reservoir, key infrastructure in Californias water system. We found reasonably high rates of total agreement between advisories by DWR and SRS, however rates of agreement varied for S2 based on algorithm. Total agreement was 83% for S3, and 52%-79% for S2. False positive and false negative rates for S3 were 12% and 23%, respectively. S2 had 12%-80% false positive rate and 0%-38% false negative rate, depending on algorithm. Using SRS-based chl-a GVs as an early indicator for possible exposure advisories and as a trigger for in situ sampling may be effective to improve public health warnings. Implementing SRS for cyanoHAB monitoring could fill temporal data gaps and provide greater spatial information not available from in situ measurements alone.

Recent studies indicate that the Asian Water Tower (AWT) is at risk due to climate change, which can negatively impact water and food security in Asia. However, there is a lack of comprehensive information on lakes' spatial and temporal changes in this region. This information is crucial for understanding the risk magnitude and designing strategies. To fill this research gap, we analyzed 89,480 Landsat images from 1977 ± 2 to 2020 ± 2 to investigate the changes in the size of lakes recharged by the AWT. Our findings showed that out of the 209 lakes larger than 50 km2, 176 (84 %) grew during the wet season and 167 (81 %) during the dry season. 74 % of expanded lakes are located in the Inner Tibetan Plateau (TP) and Tarim basins. The lakes that shrank are found mainly in the Helmand, Indus, and Yangtze basins. Over the entire period, the area of shrinkage (55,077.028 km2 in wet season, 53,986.796 km2 in dry) markedly exceeded expansion (13,000.267 km2 in wet, 11,038.805 km2 in dry), with the drastic decline of the Aral Sea being a major contributor to shrinkage, accounting for 90 % of the total loss. From 1990 ± 2 to 2020 ± 2, alpine lakes mostly expanded, plain lakes mostly shrank, with the opposite trend from 1977 ± 2 to 1990 ± 2. Glacial loss and permafrost thawing under global warming in the Inner TP, Tarim Interior, Syr Darya, and Mekong basins were strongly correlated with lake expansion. However, permafrost discontinuities may prevent significant growth of lakes in the Indus and Ganges basins despite increased recharge. Our findings point to the prominence of the risk the lakes recharged by AWT face. Taking immediate action to manage these risks and adaptation is crucial as the AWT retreats and lake recharges are slowed.

Strawberries in California are grown in specific coastal areas where land is scarce and climate change threatens future production. Strawberry growers are under pressure to adopt sustainable production strategies such as crop rotation, but this practice requires more land than back-to-back planting. The objectives of this research were to quantify the rate of crop rotation across the three main strawberry producing regions in California (Ventura, Santa Maria, and Monterey Bay), and evaluate geographic and edaphic influences on crop rotation. All strawberry fields in the main strawberry producing regions of California were identified by satellite imagery and manual inspection for the years 2017 through 2022. ArcGIS Pro was used to outline each strawberry field and compare among years to determine the period between successive strawberry plantings. Edaphic characteristics and shapefiles for surrounding fields were retrieved from public datasets. The three regions significantly differed in their rates of crop rotation. On average, 95, 52, and 25% of strawberry hectares were rotated each year in the Monterey Bay, Santa Maria, and Ventura regions, respectively. Shorter rotation lengths were associated with reduced distance from the ocean and soil with a higher percentage of sand. Based on 2 years of disease surveys, fields infested with Macrophomina phaseolina tended to be further inland than fields infested with Fusarium oxysporum f. sp. fragariae in the Monterey Bay region. This study determined that distance from the ocean and soil texture are associated with crop rotation lengths in California strawberry production. Enough land may be available in the Santa Maria and Monterey Bay regions for growers to lengthen crop rotations, but water quality, social networks, and financial considerations that were outside the scope of this study are likely to limit the ability for strawberry growers to maximize the duration of crop rotations.

Sun-induced chlorophyll fluorescence (SIF) has proven to be advantageous in estimating gross primary production, despite the lack of a stable relationship. Satellite-based SIF measurements at Level 2 offer comprehensive global coverage and are available in near real time. However, these measurements are often limited by spatial and temporal sparsity, as well as discontinuities. These limitations primarily arise from incomplete satellite trajectories. Additionally, variability in cloud cover and periodic issues specific to the instruments can compromise data quality. Two families of methods have been developed to address data discontinuity: (1) machine learning-based gap-filling techniques and (2) geostatistical techniques (various forms of kriging). The former techniques utilize the relationships between ancillary data and SIF, while the latter usually rely on the available SIF data recordings and their covariance structure to provide estimates at unsampled locations. In this study, we create a synthetic approach for SIF gap filling by hybridizing the two approaches under the umbrella of kriging with external drift. We performed leave-one-out cross-validation of the OCO-2 SIF retrieval aggregates for the entire year of 2019, comparing three methods: ordinary kriging, ML-based estimation using ancillary data, and kriging with external drift. The Mean Absolute Error (MAE) for ML, ordinary kriging, and the hybrid approach was found to be 0.1399, 0.1318, and 0.1183 mW m2 sr−1 nm−1, respectively. We demonstrate that the performance of the hybrid approach exceeds both parent techniques due to the incorporation of information from multiple resources. This use of multiple datasets enriches the hybrid model, making it more robust and accurate in handling the spatio-temporal variability and discontinuity of SIF data. The developed framework is portable and can be applied to SIF retrievals at various resolutions and from various sources (satellites), as well as extended to other satellite-measured variables.

Mountain shrublands are widespread habitats of the European Alps. Shrub encroachment into above treeline grazed lands profoundly modifies biodiversity and ecosystem functioning. Yet, mountain shrublands remain overlooked in vegetation distribution modeling because it is difficult to distinguish them from productive grasslands. Here, we used the pigment-sensitive spectral indices based on Sentinel-2 bands within a specific phenological window, to produce a high-resolution distribution map of mountain shrublands in the French Alps. We evaluated the performance of our classification using a large dataset of vegetation plots and found that our model is highly sensitive to Ericaceous species which constitute most of the dense alpine shrublands in the French Alps. Our analysis of topoclimatic and land use factors limiting the shrubland distribution at regional scale found that, consistent with the ecophysiology of shrubs, expansion is limited by a combination of water deficit and temperature. We discussed the past and current land-use implications in the observed distribution and put forward hypotheses combining climate and land-use trajectories. Our work provides a baseline for monitoring mountain shrub dynamics and exploring the response of shrublands to past and ongoing climate and land use changes.

WHOI assistant scientist Tom Bell stands with his drone on a crop of rockweed in Nahant, Mass. (Photo by Daniel Hentz, [c] Woods Hole Oceanographic Institution) IN COLLABORATION WITH HIS [...]

The present work was carried out on River Yamuna passing through Delhi-National Capital Region (Delhi-NCR) of India for a stretch of about 125 km to assess the fluvial characteristics in the highly human-dominated region for a period of 200 years with the help of historical maps, topographical maps and satellite data with integration of geographic information system (GIS) environment. Erosion, deposition and channel stability data were analyzed for 1977–1986, 1986–1996, 1996–2006, 2006–2016, and 2016–2022 period. Digital Shoreline Analysis System (DSAS) application was utilized to quantify river channel movement with average channel migration of 22.8 m/year. Westward migration is 4149.2 m maximum in length and eastward migration is about 4083.8 m. The river has migrated a total of 32.26 km2 of area during 1955-2022. The findings indicate that various human activities, such as engineering structures, sand mining, embankments, urbanization, land use/land cover changes, and canal networks, have significantly impacted the river. The DSAS application was also used to predict the position of river channel centerline in future for 2032 and 2042 with channel length of 132.5 and 141.6 km respectively. [ABSTRACT FROM AUTHOR]

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

High-resolution remote sensing images (RSI) refer to images captured from a distance, usually from an aircraft or satellite that provide details about the Earth's surface. It can be used in several application areas like environmental monitoring, urban planning, agriculture, and disaster response. In urban planning, high-resolution imagery is used to monitor the growth of urban areas or to recognize the area that requires infrastructure improvement. Vehicle detection is a significant way of understanding high-resolution RSIs. Vehicle detection and classification on high-resolution RSI is a difficult task that needs a group of computer vision (CV), image processing, and machine learning (ML) algorithms. Deep convolutional neural network (DCNN) based techniques have attained recent outcomes in many object detection datasets and have enriched several CV tasks. This article designed and developed a sparrow search optimization algorithm with deep learning for vehicle type detection and classification (SSOADL-VTDC) technique on high-resolution remote sensing images. The presented SSOADL-VTDC technique examines the high-quality RSIs for the accurate detection and classification of vehicles. To accomplish this, the SSOADL-VTDC technique employs a YOLOv5 object detector with a Residual Network as a backbone approach. In addition, the SSOADL-VTDC technique uses SSOA based hyperparameter optimizer designed for the parameter tuning of the YOLOv5 model. For the vehicle classification process, the SSOADL-VTDC technique exploits the softmax classifier. The simulation validation of the SSOADL-VTDC approach was validated on a high-resolution RSI dataset and the outcomes demonstrated the greater of the SSOADL-VTDC methodology in terms of different measures. [ABSTRACT FROM AUTHOR]

Volcanic degassing and explosive eruptions inject significant amounts of gas and ash into the atmosphere, impacting the local environment and atmospheric dynamics from local to global scales. While ground- and satellite-based remote sensing systems are key to describing explosive volcanism and assessing associated hazards, direct in situ measurements inside volcanic clouds are not possible with these methods. This study presents an innovative approach using an Unoccupied Aircraft System (UAS) for (i) airborne ash sampling and (ii) measurements of aerosol and gas concentrations (AeroVolc system). Commercial instruments (DJITM Matrice 30 Unoccupied Aerial Vehicle (UAV), AlphasenseTM N3 Optical Particle Counter OPC, SoarabilityTM Sniffer4D Mini2 multigas hardware) were combined with custom-built ash collectors and particle counters to enable a more detailed analysis of volcanic clouds. Here we showcase the deployment of our UAS on Sakurajima (Japan) and Etna (Italy), two volcanoes known for their frequent explosive eruptions and persistent degassing activity, to demonstrate how this approach enables in situ , high-resolution sample and data collection within challenging environments. Results provide grain size distributions (GSDs), information on the occurrence of particle aggregation, as well as solid aerosol (PM1, PM2.5, and PM10) and gas (SO2 and CO2) concentrations. Depending on whether the UAS was operated within or below ash- and/or gas-rich clouds, different insights were gained that open up new perspectives for volcanological research. These insights include the composition, concentration, generation, dispersion and sedimentation patterns of volcanic clouds. [ABSTRACT FROM AUTHOR]

Societal Impact Statement Summary Addressing the burning environmental crisis, we explore how the ‘extreme sport’ of paramotoring can enhance and accelerate scientific exploration with minimal environmental impact compared to off‐road vehicles. Our study demonstrates the scientific potential of paramotoring to access fragile desert ecosystems and investigate unrecorded habitats and species. Comparisons with 4 × 4s showed significant reductions in CO2‐eq emissions for longer missions and ninefold faster travel times. Unlike off‐road vehicles, which can damage the equivalent of over one football pitch in area per linear kilometre driven, paramotors cause minimal damage. Integrating extreme sports and science can accelerate data and specimen collection for more effective habitat conservation. This has the potential to spark discoveries and engagement across diverse communities. In the face of an urgent climate and environmental crisis, we explore the potential of paramotoring to expand scientific reach and collection capability without the environmental harm associated with off‐road vehicles. In Peru's fog oasis desert, we brought together paramotor experts and scientists to conduct missions involving monitoring, plant sampling, surveying, sensor placement and transportation. We compared the environmental impact and time taken by paramotoring with surveys conducted using off‐road vehicles and walking. Shorter paramotor missions showed small differences in CO2 equivalents and time efficiency compared to off‐road vehicles. However, longer missions (28 km from base camp) revealed up to nine times faster travel and two thirds less CO2 equivalent emissions. Notably, off‐road vehicles left a substantial environmental footprint (700 to 8000 m2 per km), whilst paramotors had a minimal impact, with a tiny surface ‘footprint’ of just a few square metres, representing orders of magnitude (1000 to 10,000) less environmental impact. With basic training in identification and sampling, paramotorists collected plant specimens that are invaluable for ongoing and future scientific study. Whilst logistical and safety challenges in transporting scientists via paramotors need further investigation, the benefits, especially compared to surface travel, are evident. Integrating extreme sports into scientific endeavour promises wider and more comprehensive exploration, new discoveries and increased engagement across diverse communities—and in summary—offers significant potential to address urgent environmental challenges. [ABSTRACT FROM AUTHOR]

Mosquito‐borne diseases contribute substantially to the global burden of disease, and are strongly influenced by environmental conditions. Ongoing and rapid environmental change necessitates improved understanding of the response of mosquito‐borne diseases to environmental factors like temperature, and novel approaches to mapping and monitoring risk. Recent development of trait‐based mechanistic models has improved understanding of the temperature dependence of transmission, but model predictions remain challenging to validate in the field. Using West Nile virus (WNV) as a case study, we illustrate the use of a novel remote sensing‐based approach to mapping temperature‐dependent mosquito and viral traits at high spatial resolution and across the diurnal cycle. We validate the approach using mosquito and WNV surveillance data controlling for other key factors in the ecology of WNV, finding strong agreement between temperature‐dependent traits and field‐based metrics of risk. Moreover, we find that WNV infection rate in mosquitos exhibits a unimodal relationship with temperature, peaking at ~24.6–25.2°C, in the middle of the 95% credible interval of optimal temperature for transmission of WNV predicted by trait‐based mechanistic models. This study represents one of the highest resolution validations of trait‐based model predictions, and illustrates the utility of a novel remote sensing approach to predicting mosquito‐borne disease risk. [ABSTRACT FROM AUTHOR]

Non‐invasive wide‐field imaging through dynamic random media is a sought‐after goal with important applications ranging from medical diagnosis to remote sensing. However, some existing methods, such as speckle correlation‐based techniques, are limited in field of view due to the memory effect; while some other methods, such as wavefront shaping and transmission matrix techniques, face considerable challenges when applied in dynamic scenarios because of the complexity involved in modulation and measurement. These limitations significantly impede the effectiveness and applicability of these approaches. Here, the concept of virtual reference light (VRL), which allows for the reconstruction of the original object with just a single‐shot detection of the speckle is proposed. Experimental results demonstrate that the imaging field achieves a 3.8‐fold memory effect range. In the experimental setup, the light source and detector are positioned on one side of the random medium, while the sample is placed on the opposite side, enabling non‐invasive detection. Imaging results with both static and dynamic scattering media are presented to verify the feasibility of the proposed method, offering an effective solution for real‐time target imaging and detection. [ABSTRACT FROM AUTHOR]

Wheat stripe rust (WSR), a fungal disease capable of inflicting severe crop loss, threatens most of global wheat production. Breeding for genetic resistance is the primary defense against stripe rust infection. Further development of rustresistant wheat varieties depends on the ability to accurately and rapidly quantify rust resilience. In this study we demonstrate the ability of visible through shortwave infrared reflectance spectroscopy to effectively provide high-throughput classification of wheat stripe rust severity and identify important spectral regions for classification accuracy. Random forest models were developed using both leaf-level and canopy-level hyperspectral reflectance observations collected across a breeding population that was scored for WSR severity using 10 and 5 severity classes, respectively. The models were able to accurately diagnose scored disease severity class across these fine scoring scales between 45-52% of the time, which improved to 79-96% accuracy when allowing scores to be off-by-one. The canopy-level model demonstrated higher accuracy and distinct spectral characteristics relative to the leaf-level models, pointing to the use of this technology for field-scale monitoring. Leaf-level model performance was strong despite clear variation in scoring conducted between wheat growth stages. Two approaches to reduce predictor and model complexity, principal component dimensionality reduction and backward feature elimination, were applied here. Both approaches demonstrated that model classification skill could remain high while simplifying high-dimensional hyperspectral reflectance predictors, with parsimonious models having approximately 10 unique components or wavebands. Through the use of a high-resolution infection severity scoring methodology this study provides one of the most rigorous tests of the use of hyperspectral reflectance observations for WSR classification. We demonstrate that machine learning in combination with a few carefully-selected wavebands can be leveraged for precision remote monitoring and management of WSR to limit crop damage and to aid in the selection of resilient germplasm in breeding programs. [ABSTRACT FROM AUTHOR]

In low-resolution remote sensing images under complex lighting conditions, there is a similarity in spectral characteristics between non-landslide areas and landslide bodies, which increases the probability of misjudgment in the identification process of shallow landslide bodies. In order to further improve the accuracy of landslide identification, a shallow landslide remote sensing identification method based on an improved Otsu algorithm and multi-feature threshold is proposed for the temporary treatment project of the Yangjunba disaster site in Leshan City. Using Retinex theory, remote sensing images are enhanced with local linear models and guided filtering; then, multi-feature scales and sliding window calculations of opening and closing transformations identify potential landslide areas, which are finally segmented using the Otsu algorithm. Through experimental verification, the method proposed in this article can clearly segment the target object and background after binary segmentation of remote sensing images. The recognition rate of shallow landslide bodies is not less than 95%, indicating that the method proposed in this article is relatively accurate in identifying shallow landslide bodies in the research area and has good application effects. [ABSTRACT FROM AUTHOR]

In recent years, deep learning has significantly reshaped numerous fields and applications, fundamentally altering how we tackle a variety of challenges. Areas such as natural language processing (NLP), computer vision, healthcare, network security, wide-area surveillance, and precision agriculture have leveraged the merits of the deep learning era. Particularly, deep learning has significantly improved the analysis of remote sensing images, with a continuous increase in the number of researchers and contributions to the field. The high impact of deep learning development is complemented by rapid advancements and the availability of data from a variety of sensors, including high-resolution RGB, thermal, LiDAR, and multi-/hyperspectral cameras, as well as emerging sensing platforms such as satellites and aerial vehicles that can be captured by multi-temporal, multi-sensor, and sensing devices with a wider view. This study aims to present an extensive survey that encapsulates widely used deep learning strategies for tackling image classification challenges in remote sensing. It encompasses an exploration of remote sensing imaging platforms, sensor varieties, practical applications, and prospective developments in the field. [ABSTRACT FROM AUTHOR]

Effective extraction of building from remote sensing images requires both global and local information. Despite convolutional neural networks (CNNs) excelling at capturing local details, their intrinsic focus on local operations poses challenge in effectively extracting global features, especially in the context of large‐scale buildings. In contrast, transformers excel at capturing global information, but compared to CNNs, they tend to overly rely on large‐scale datasets and pre‐trained parameters. To tackle the challenge, this paper presents the multi‐scale and dual‐branch feature fusion network (MDTrans). Specifically, the CNN and transformer branches are integrated in a dual‐branch parallel manner during both encoding and decoding stages, local information for small‐scale buildings is extracted by utilizing Dense Connection Blocks in the CNN branch, while crucial global information for large‐scale buildings is effectively captured through Swin Transformer Block in the transformer branch. Additionally, Dual Branch Information Fusion Block is designed to fuse local and global features from the two branches. Furthermore, Multi‐Convolutional Block is designed to further enhance the feature extraction capability of buildings with different sizes. Through extensive experiments on the WHU, Massachusetts, and Inria building datasets, MDTrans achieves intersection over union (IoU) scores of 91.36%, 64.69%, and 79.25%, respectively, outperforming other state‐of‐the‐art models. [ABSTRACT FROM AUTHOR]

Accurate identification of coastal hyperspectral remote sensing targets plays a significant role in the observation of marine ecosystems. Deep learning is currently widely used in hyperspectral recognition. However, most deep learning methods ignore the complex correlation and data loss problems that exist between features at different scales. In this study, Multi-scale attention reconstruction convolutional network (MARCN) is proposed to address the above issues. Firstly, a multi-scale attention mechanism is introduced into the network to optimize the feature extraction process, enabling the network to capture feature information at different scales and improve the target recognition performance. Secondly, the reconstruction module is introduced to fully utilize the spatial and spectral information of hyperspectral imagery, which effectively solves the problem of losing spatial and spectral information. Finally, an adaptive loss function, coupling cross-entropy loss, center loss, and feature space loss is used to enable the network to learn the feature representation and improve the accuracy of the model. The experimental results showed that the effectiveness of MARCN was validated with a recognition rate of 96.62%, and 97.92% on the YRE and GSOFF datasets. [ABSTRACT FROM AUTHOR]

In an era marked by growing global population and climate variability, ensuring food security has become a paramount concern. Rice, being a staple crop for billions of people, requires accurate and timely yield prediction to ensure global food security. This study was undertaken across two rice crop seasons in the Udham Singh Nagar district of Uttarakhand state to predict rice yield at 45, 60 and 90 days after transplanting (DAT) through machine learning (ML) models, utilizing a combination of optical and Synthetic Aperture Radar (SAR) data in conjunction with crop biophysical parameters. Results revealed that the ML models were able to provide relatively accurate early yield estimates. For summer rice, eXtreme gradient boosting (XGB) was the best-performing model at all three stages (45, 60, and 90 DAT), while for kharif rice, the best-performing models at 45, 60, and 90 DAT were XGB, Neural network (NNET), and Cubist, respectively. The combined ranking of ML models showed that prediction accuracy improved as the prediction date approaches harvest, and the best prediction of yield was observed at 90 DAT for both summer and kharif rice. Overall rankings indicate that for summer rice, the top three models were XGB, NNET, and Support vector regression, while for kharif rice, these were Cubist, NNET, and Random Forest, respectively. The findings of this study offer valuable insights into the potential of the combined use of remote sensing and biophysical parameters using ML models, which enhances food security planning and resource management by enabling more informed decision-making by stakeholders such as farmers, policy planners as well as researchers. [ABSTRACT FROM AUTHOR]

Nitrogen is a key nutrient for crop growth. Excessive or insufficient nitrogen affects crop growth, yield, and quality. Additionally, excessive nitrogen fertilizer can cause soil and water pollution. Applying panicle fertilizer during the late jointing stage can promote rice panicle growth. Therefore, accurately and timely monitoring of nitrogen status in rice fields during the late jointing stage and timely optimizing fertilization strategies is crucial for ensuring rice yield and environmental protection. This paper integrates multimodal data from unmanned aerial vehicle (UAV) remote sensing and ground observations to construct inversion models for leaf nitrogen content (LNC) and plant nitrogen content (PNC) of rice at the late jointing stage. The research was conducted at the Shapu Experimental Base of the Agricultural Science Research Institute in Zhaoqing City, Guangdong Province, with two field experiments carried out during the late rice seasons of 2021 and 2022. Each of Experiment 1 (2021) and Experiment 2 (2022) included 30 experimental plots, designed with 5 nitrogen fertilizer gradients, 2 planting densities, and 3 replications. Phosphorus and potassium fertilizers were applied uniformly across all plots. UAVs equipped with multispectral and RGB cameras were used to acquire remote sensing images of rice canopies during the late jointing stage. Vegetation indices (VIs) and texture feature values (TFVs) were extracted from the multispectral images, with TFVs derived using the gray level co-occurrence matrix (GLCM) method. Texture indices (TIs) were then constructed by combining TFVs. RGB images were used to generate digital surface models (DSM) for bare ground (pre-transplant) and rice fields (late jointing stage). These DSMs, combined with ground reference methods, were used to construct crop surface models (CSM) to derive estimated canopy heights (ECH) for each plot. Manually collected data included measured canopy height (MCH) and field nitrogen management data (FN) used as ground observations. For each experimental plot, three representative rice plants were selected as samples. After removing the roots, the leaves and stems were separated and dried at 85℃ to a constant weight, which was recorded as the aboveground biomass of the leaves and stems. The true values of leaf nitrogen content and stem nitrogen content were obtained using the Kjeldahl method. Combining these values with the dry weight data, the true values of plant nitrogen content were calculated. The maximal information coefficient (MIC) was used as an evaluation metric for feature assessment and selection. Random forest regression algorithms were employed to construct inversion models for rice LNC and PNC, respectively, using the coefficient of determination (R2), root mean squared error (RMSE), and mean absolute error (MAE) as model evaluation metrics. The analysis and experimental results indicate: TIs constructed using combinations of TFVs significantly enhanced the correlation between texture information and LNC and PNC. When the UAV flight height was 100 m, the Ratio Texture Index constructed using a 9×9 sliding window size in the GLCM method showed the best performance, improving the MIC value by 11.48% compared to the best TFV. For conventional machine-transplanted rice planting density, the correlation between TIs and LNC and PNC was best when the GLCM sliding window size was set to 9×9 or 11×11 at a UAV flight height of 100 m. The ECH derived from the CSM showed a high correlation with the manual MCH in the field. Including canopy height (MCH or ECH) as an input feature in the random forest regression model significantly improved the inversion accuracy of rice nitrogen content. The ECH extracted from the CSM showed high estimation accuracy (R² = 0.77, RMSE = 3.4 cm, MAE = 2.8 cm). The inclusion of canopy height (MCH or ECH) in the model construction improved the inversion accuracy for PNC more significantly compared to LNC. Integrating UAV remote sensing and ground observation multimodal data, the random forest regression algorithm significantly improved the inversion accuracy of rice LNC and PNC at the late jointing stage. Considering both inversion accuracy and operational convenience, it is recommended to use a feature combination of VI+TI+ECH+FN in field production. Compared to using VI alone, this feature combination improved R² by 6.73%, and reduced RMSE and MAE by 13.62% and 14.68%, respectively, for LNC inversion. For PNC inversion, R2 was improved by 12.53%, and RMSE and MAE were reduced by 22.09% and 19.80%, respectively. The results demonstrate that constructing random forest regression models by integrating UAV remote sensing and ground observation multimodal data can accurately detect rice LNC and PNC, providing a scientific basis for rice field management and fertilization decision-making. [ABSTRACT FROM AUTHOR]

Enhancing rotational measurement resolution and broadening the detectable spectral range are two critical and unresolved matters within the realm of motion perception. The rotational Doppler effect (RDE) is combined with the harmonic generation process to create a rotational measurement scheme that offers flexible detection wavelength conversion, exponential improvement of measurement resolution, and real‐time display of detection results. In the experiments, a cascaded second harmonic generation process is employed to attain a fourfold enhancement in rotational resolution and demonstrate how low‐cost silicon‐based detectors can be used for real‐time detection of infrared objects. This scheme employs a Gaussian beam within the nonlinear process to achieve high conversion efficiency, thereby enabling potential for subsequent cascade amplification. Additionally, it is fully compatible with existing RDE schemes, allowing for co‐amplification of rotational resolution at both the front‐end and back‐end. This research could offer a more precise and cost‐effective method for remote sensing detection. [ABSTRACT FROM AUTHOR]

ABSTRACT Recent advancements in remote sensing and artificial intelligence can potentially revolutionize the automated detection of archaeological sites. However, the challenging task of interpreting remote sensing imagery combined with the intricate shapes of archaeological sites can hinder the performance of computer vision systems. This work presents a computer vision system trained for efficient hillfort detection in remote sensing imagery. Equipped with an adapted multimodal semantic segmentation model, the system integrates LiDAR‐derived LRM images and aerial orthoimages for feature fusion, generating a binary mask pinpointing detected hillforts. Post‐processing includes margin and area filters to remove edge inferences and smaller anomalies. The resulting inferences are subjected to hard positive and negative mining, where expert archaeologists classify them to populate the training data with new samples for retraining the segmentation model. As the computer vision system is far more likely to encounter background images during its search, the training data are intentionally biased towards negative examples. This approach aims to reduce the number of false positives, typically seen when applying machine learning solutions to remote sensing imagery. Northwest Iberia experiments witnessed a drastic reduction in false positives, from 5678 to 40 after a single hard positive and negative mining iteration, yielding a 99.3% reduction, with a resulting F1 score of 66%. In England experiments, the system achieved a 59% F1 score when fine‐tuned and deployed countrywide. Its scalability to diverse archaeological sites is demonstrated by successfully detecting hillforts and other types of enclosures despite their typical complex and varied shapes. Future work will explore archaeological predictive modelling to identify regions with higher archaeological potential to focus the search, addressing processing time challenges. [ABSTRACT FROM AUTHOR]

Deep learning (DL)-based approaches are notable for their ability to establish feature associations without relying on physical constraints, unlike traditional strategies that are complex and dependent on expert experience. However, three main challenges hinder the versatility of semantic segmentation models. First, the targets in these images are dense and exist at varying spatial scales, which imposes higher demands on the model for accurate segmentation across scales. Second, the segmentation of small targets in the images is often overlooked, leading to a compromise between fine segmentation and model efficiency. Lastly, the data-intensive nature of remote sensing images and the resource-intensive operations of large-scale networks impose significant communication and computation burdens on edge devices, which may not have sufficient resources to handle them effectively. To address these challenges, this paper proposes a lightweight semantic segmentation method for remote sensing images to achieve high-precision segmentation for multi-scale targets while maintaining low computational complexity. The main components include: (1) embedding the inverted residual block structure to minimize the number of model parameters and computational costs; (2) introducing the parallel irregular space pyramid pooling module to efficiently aggregate multi-scale contextual information for fine-grained recognition of small targets; and (3) embedding transfer learning into the encoder-decoder structure to speed up the convergence rate and improve multi-scale feature fusion capability, thereby reducing semantic information loss. The proposed lightweight method has been extensively tested on real-world high-resolution remote sensing datasets. It achieved PA, MPA, MIoU, and FWIoU scores of 87.90%, 75.76%, 66.29%, and 78.81% on the Vaihingen dataset; 87.03%, 85.31%, 74.85%, and 77.54% on the Potsdam dataset; and 95.37%, 83.33%, 75.70%, and 91.31% on the Aeroscapes dataset. Compared to other popular semantic segmentation models, the proposed method achieved the highest values in all four evaluation indicators, demonstrating its effectiveness and superiority. [ABSTRACT FROM AUTHOR]

Recently, U-Net architecture has been extensively explored for remote sensing (RS) image haze removal, demonstrating remarkable performance. However, most existing RS image haze removal methods based on the U-Net fail to fully utilize feature information extracted in the encoding layers during decoding, resulting in unsatisfactory haze removal results. Moreover, most haze removal algorithms neglect the interaction of cross-level feature information, which is particularly important for scene recovery and context information constraints. To address these issues, this paper presents an Embedded U-shaped Network with Cross-Hierarchical Feature Adaptation Fusion Network (EUCHA). Specifically, an Embedded U-shaped Network Framework (EUNF) is proposed to fuse the features extracted from different scale encoding layers as supplementary information into the corresponding decoding layers by embedding multiple parallel U-shaped subnetworks, which alleviates feature information dilution during the decoding process and enhances the network receptive field. Furthermore, we propose a Cross-Hierarchical Feature Adaptive Fusion (CHAF) module, which effectively and adaptively fuses multiple adjacent hierarchical features extracted by channel attention and pixel attention through learnable factors to enhance the expressive ability of features. Experiments were conducted on both real and synthetic datasets and compared with the nine most advanced algorithms. The results showed that EUCHA algorithm performs better in removing artefacts in both RS images and natural images. The source code is available at . [ABSTRACT FROM AUTHOR]

The fall armyworm (FAW), Spodoptera frugiperda (J.E. Smith), invasion endangered the maize production worldwide, including India. The objective of this study was to quantify the FAW damage severity and its impact on leaf area index (LAI), biomass and grain yield of maize and to detect the field damage using high-resolution multispectral spaceborne remote sensing data. Maize growing fields in the Kurnool District of Andhra Pradesh and the Gadwal District of Telangana, India, were randomly surveyed to collect detailed ground-truth information. Foliar damage due to FAW was recorded, and the fields were categorized into various severity grades (healthy, low, medium and severe). FAW infestation caused significant change in LAI between the severity grades, which formed the basis for its damage detection using multispectral spaceborne remote sensing. Severe FAW infestation caused significant reduction in LAI, biomass and grain yield ranging between 36.9 and 39.9% compared to healthy grade. The infestation at the leaf collar (LC) stage caused significant yield loss of up to 26.5% compared to the tassel initiation (TI) and tasselling and silking (TS) stages. Canopy spectral reflectance from healthy and FAW-infested plants showed significant differences in the visible and near infrared (NIR) regions. A reflectance peak was observed in the NIR region of healthy plants compared to infested plants. Among various spaceborne vegetation indices, the Soil Adjusted Vegetation Index (SAVI) performed better in identifying the FAW infestation (R2 = 0.61**), biomass (R2 = 0.70**) and yield loss (R2 = 0.82**). These findings indicate the feasibility of utilizing multispectral remote sensing data for monitoring FAW infestation on a spatial scale, thus enabling the site-specific management. [ABSTRACT FROM AUTHOR]

As a renewable energy source, ocean wind energy plays an important role in addressing challenges such as global energy shortages and climate warming. In the past decade, the offshore wind power industry has developed rapidly. However, its development has also inevitably affected local social, economic and environmental aspects. Therefore, a timely understanding of offshore wind power dynamics development is crucial for its healthy and sustainable development. Based on this, this study designs and develops a more economical, reliable and real-time offshore wind turbine (OWT) extraction method by combining deep learning and the Google Earth Engine (GEE) cloud computing platform. The method consists of two main steps. The first part utilizes multiple semantic segmentation models to construct a multi-model detection method to initially detect OWTs. The second part utilizes the GEE cloud computing platform for installation time detection and secondary purification processing of the preliminary results. The results show that the number of global OWTs reached 13,609 by 2023, and the accuracy of the detection results reached 99.93%. China has been the fastest-growing country in offshore wind power in the last decade, from installing only 4 units in 2015 to installing 6,775 units in 2023 and surpassing the UK in 2020 and becoming the country building the most OWTs worldwide. Currently, 85% of the world's OWTs are located in China and European North Sea waters. Additionally, other regions have great potential for offshore wind development. Finally, this study provides the world's most up-to-date and complete OWT dataset, which can provide data support for research on marine ecological and environmental protection, marine spatial planning, and socioeconomic benefits. [ABSTRACT FROM AUTHOR]

Radar is a crucial tool for remote sensing and monitoring of marine environments. However, its effectiveness is significantly influenced by sea clutter. The complex interplay between radar parameters and various maritime environmental factors gives rise to a dynamic and intricate sea clutter pattern. The conventional approach to sea clutter prediction only considers the temporal dependence, neglecting the spatial changes. To address this limitation, this study proposes the Fusion of Fourier Transform and Graph Neural Network (FFTaGNN) to enhance the accuracy of multi-dimensional sea clutter data forecasting. FFTaGNN captures the correlations and time dependencies among sequences in the spectral domain. By combining the discrete Fourier transform (DFT) and graph Fourier transform (GFT), it extracts the temporal correlation characteristics and establishes correlations between multidimensional sea clutter data sequences. Importantly, FFTaGNN can automatically discover data correlations between sequences without relying on predetermined priors. To validate the effectiveness of the model, an experimental verification process is conducted, considering different grazing angles and sea clutter High Range Resolution Profile (HRRP) data. The results of the experiment demonstrate that the proposed strategy achieves a minimum Root Mean Square Error (RMSE) of 0.0574 in predicting sea clutter HRRP data. This technique holds great potential in effectively suppressing sea clutter, thereby enhancing the overall performance of radar systems in marine environments and small target detection capabilities at the sea surface. [ABSTRACT FROM AUTHOR]

Vegetation height, and its spatial and temporal changes, is an important environmental parameter required for understanding natural habitats, estimating carbon stores and monitoring forestry activities. Recent satellite LiDAR altimetry sensors have discontinuous spatial coverage but can be combined with spatially complete remote sensing data to extrapolate to large regions. Earlier studies have focused on producing a single spatially continuous vegetation height product. This research builds on past studies, using Landsat (annual surface reflectance and fractional cover products) and the Global Ecosystem Dynamics Investigation (GEDI) data to generate annual vegetation height layers from 1988 to 2022. GEDI data for 2019 were used to train and validate the model, resulting in a root mean square error (RMSE) of 5.45 m, mean absolute error (MAE) of 3.82 m, and coefficient of determination (R2) of 0.63. This accuracy reduces when the modelled height for 2020, 2021, and 2022 is compared to GEDI data for the same years (RMSE = 6.08–6.29 m, MAE = 4.36–4.73 m, and R2 = 0.48–0.54). Validation with independent field measurements across Australia from 2011 to 2021 shows an RMSE, MAE, and R2 of 8.2 m, 5.2 m, and 0.48, respectively. One source of error is the saturation of the Landsat signal in tall, closed canopy vegetation. While model accuracy is correlated with plot-based vegetation height measurements, results indicate that accuracy reduces for the years outside of the model calibration year (i.e. 2019). When compared to other vegetation height products (also produced using GEDI and spatial remote sensing data) from three independent published studies (one for 2009, one for 2019, and one for 2020), the model developed here tends to estimate 2–4 m taller than the first two studies and around 5 m shorter when compared to the third study. This investigation demonstrates the potential to produce multiyear vegetation height at a continental scale but also highlights the large uncertainty in modelled estimates especially when extrapolating to years other than the model calibration year. [ABSTRACT FROM AUTHOR]

The constraints of spatiotemporal heterogeneity and spatial resolution constitute two crucial challenges in the establishment of remote sensing inversion models. Spatiotemporal heterogeneity gives rise to an inadequate generalization capacity of remote sensing models, demanding extensive manual parameter adjustment for each model construction. This not only escalates the task's work intensity but also leads to unstable performance. The limited spatial resolution of remote sensing images leads to suboptimal inversion accuracy for sampling points influenced by mixed pixel effects. To tackle these problems, we take the case of non-photosensitive water quality parameter inversion in the narrow rivers of Longnan area. By integrating advanced Hyper-Parameter Optimization (HPO) techniques, such as Optuna from machine learning, an inversion model was developed, incorporating the bands of Sentinel-2 and Sentinel-3 as model features. Among these features, bands with lower spatial resolution are employed to furnish surrounding information, thereby enhancing the inversion accuracy. The research outcomes demonstrate that: 1) The model constructed based on the HPO method, Optuna, attained favourable inversion results, with R2 values of 0.68, 0.77, 0.35, and 0.60 for Total Nitrogen (TN), Total Phosphorus (TP), Ammonia Nitrogen (NH3-N), and Chemical Oxygen Demand (COD), respectively. 2) The fusion of Sentinel-2 and Sentinel-3 data enhanced the inversion accuracy compared to using them separately, highlighting the considerable significance of multi-source data fusion methods in improving inversion accuracy. This research fills a void in the remote sensing inversion domain and lays the groundwork for future endeavours. [ABSTRACT FROM AUTHOR]