Remote Sensing Applications-Society and Environment最新文献

{"title":"Comparison between machine learning classification and trajectory-based change detection for identifying eucalyptus areas in Landsat time series","authors":"Debora da Paz Gomes Brandão Ferraz,&nbsp;Raúl Sánchez Vicens","doi":"10.1016/j.rsase.2024.101444","DOIUrl":"10.1016/j.rsase.2024.101444","url":null,"abstract":"<div><div>In forestry, where species management has inter-annual durations, time series longer than one year have been used to map planted areas, estimate biophysical parameters, and determine planting age. Eucalyptus plantations have characteristics that enhance the use of time series in their classification, such as clear-cutting before planting or previous rotation and the rapid growth of large vegetation cover, which remains stable throughout the rotation period. This article compares the performance of two classification methods for mapping Eucalyptus areas: an object-oriented classification (GEOBIA) using products generated by the LandTrendr change detection algorithm based on trajectories and a classification using machine learning (random forest). Using a Landsat time series from 1985 to 2020, tests were conducted in a pilot area in Rio de Janeiro, Brazil. Both methods showed high accuracy in detecting Eucalyptus areas. However, the trajectory-based classification proved slightly superior, achieving a global accuracy of 0.988 and an F-Score of 0.975, while the classification using the random forest algorithm achieved a global accuracy of 0.954 and an F-score of 0.849. Regarding identifying the initial year of planting, both methods proved effective without showing significant differences (p-value = 0.1003). However, detecting the initial year using the LandTrendr algorithm proved more assertive. Both methods revealed periods of increase and stabilization in Eucalyptus planting throughout the time series, proving promising for determining the location and age of each stand and, thus, obtaining information about the time of use of that area for Eucalyptus cultivation.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101444"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ViT-ChangeFormer: A deep learning approach for cropland abandonment detection in lahore, Pakistan using Landsat-8 and Sentinel-2 data","authors":"Mannan Karim ,&nbsp;Haiyan Guan ,&nbsp;Jiahua Zhang ,&nbsp;Muhammad Ayoub","doi":"10.1016/j.rsase.2025.101468","DOIUrl":"10.1016/j.rsase.2025.101468","url":null,"abstract":"<div><div>Cropland abandonment poses significant environmental, economic, and social challenges globally. As urbanization encroaches on agricultural areas, understanding the dynamics of abandoned croplands and accurately classifying and detecting them are essential for informed sustainable land use and effective policy development. However, traditional methods struggle to identify abandoned croplands due to temporal variability, limited spectral data and challenges in land cover variations. To address these challenges, we introduced an innovative deep learning approach that combines a Vision Transformer (ViT) with ChangeFormer for the classification and change detection of cropland abandonment using Landsat-8 and Sentinel-2 datasets in Lahore, Pakistan. We employed ViT for image classification, enhancing its efficacy through the incorporation of Vegetation Indices (VIs). This integration led to notable improvements in F1 score and Overall Accuracy (OA), elevating them from 86% and 88%to 92% and 95% respectively. Subsequently, ViT-generated classified rasters facilitated in identification of abandoned lands using ChangeFormer model. The direct comparison showcased a significant enhancement in ChangeFormer's performance, with F1 score and OA escalating from 91% and 90% to 97.5% and 96%, respectively. The improvment was particularly evident when testing ChangeFormer with ViT-generated rasters compared to raw imagery for binary change detection. The study identified 32,043 ha of abandoned cropland (14,613 in 2019 and 17,430 in 2024), with 16.35% converted to built-up areas in 2024. Urbanization was the primary driver, followed by conversions to barren land and water bodies. While our approach improves cropland abandonment detection, addressing unavailability of high-resolution imagery, computational costs, and integrating socio-economic and climate factors could enhance its accuracy and effectiveness.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101468"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integration of multi-method ASTER data analysis and geometric average modeling for hydrothermal alteration mapping and mineral prospectivity assessment of copper deposits, Anti-Atlas, Morocco","authors":"Lahsen Achkouch ,&nbsp;Ahmed Attou ,&nbsp;Hafid Mezougane ,&nbsp;Mohammed Ouchchen ,&nbsp;Younesse El Cheikh ,&nbsp;Younes Mamouch ,&nbsp;Abdelhamid Bajadi ,&nbsp;Bouchra Dadi ,&nbsp;Rachid Ahmed ,&nbsp;Behnam Sadeghi","doi":"10.1016/j.rsase.2025.101467","DOIUrl":"10.1016/j.rsase.2025.101467","url":null,"abstract":"<div><div>Satellite imagery is a crucial tool for mineral exploration, as it enables the identification of mineralization systems through hydrothermal alteration mapping. This study focuses on the Tikirt region within the Anti-Atlas belt, well-documented for its copper mineralization, to produce a predictive mineral prospectivity map. Advanced processing of ASTER (Advanced Spaceborne Thermal Emission and Reflection Radiometer) satellite imagery was conducted to detect key alteration minerals, including argillic, phyllic, propylitic, and iron oxide. Spectral analysis techniques such as Spectral Feature Fitting (SFF), Matched Filtering (MF), Least-Squares Fitting (LS-Fit), and Constrained Energy Minimization (CEM) were utilized alongside the references spectra from the USGS library to delineate alteration zones. These were integrated using the geometric average model to generate a comprehensive prospectivity map highlighting areas with high mineralization potential. Field validation and laboratory analyses, confirmed the accuracy of the predictive map, demonstrating a strong alignment between high-potential zones, mapped faults, and mineralization occurrences. Assessment of the accuracy of alteration mapping indicates a satisfactory level of consistency with reference data (overall accuracy = 80%) and a high level of agreement (Kappa coefficient = 73.3%). Notably, the study identified several new areas with significant potential for copper mineralization, particularly associated with Neoproterozoic formations located in the northeast, northwest, south, and southeast of the study area. The results revealed a strong correlation between ASTER image processing and field/laboratory data, underscoring the effectiveness of integrating ASTER imagery with advanced spectral analysis for regional-scale mineral prospectivity. This integrated approach offers significant potential for guiding future exploration projects.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101467"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing the coherency of different El Niño events with vegetation health using time-series remote sensing data and wavelet coherency analysis in part of Southeast Asia","authors":"Sanjiwana Arjasakusuma,&nbsp;Yusri Khoirurrizqi,&nbsp;Tsamarah Huwaida","doi":"10.1016/j.rsase.2025.101460","DOIUrl":"10.1016/j.rsase.2025.101460","url":null,"abstract":"<div><div>El Niño Southern Oscillation (ENSO) is a cyclic period of warm and cold events that affect the seasonal global weather patterns due to the weaker trade winds in Pacific Oceans. During the warm ENSO events, or El Niño, regions including Southeast Asia, are exposed to the reduced precipitation and warmer temperatures, which able to affect the vegetation dynamics. El Niño warm events can occur in different magnitudes and intensities but the impacts of different warm ENSO magnitudes to vegetation health is rarely studied. This study explored the coherency of different El Niño events as indicated by ENSO indices with vegetation health in Indonesia by using wavelet semblance analysis (WSA). Our results suggested that short-duration and strong ENSO events highly affected the vegetation dynamics, and potential coupled impact of ENSO warm event and Indian Ocean Dipole (IOD) such as in 2006 can influence the vegetation health. The 1982, 1997–1998 and 2015–2016 strong ENSO events affected for more than 40 % of vegetation health in Indonesia, while 2006's combined weak-ENSO and IOD events affected up to 44 % of vegetation health. From the total 40–59 % areas that were affected in 1997–1998 ENSO's event, 38–56 % was Evergreen Broadleaf Forests (EBF). This indicates that strong magnitude of El Niño combined with IOD could increase the impact of climate anomalies to the vegetation health.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101460"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143101041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integration of PRISMA hyperspectral satellite data with ground based geological investigation for mapping alteration minerals associated with the Neem-ka-Thana Cu belt in Rajasthan, India","authors":"Angana Saikia ,&nbsp;Ajanta Goswami ,&nbsp;Bijan Jyoti Barman ,&nbsp;Kanishka Hans Sugotra ,&nbsp;Hrishikesh Kumar","doi":"10.1016/j.rsase.2024.101421","DOIUrl":"10.1016/j.rsase.2024.101421","url":null,"abstract":"<div><div>Hydrothermal deposits are commonly associated with specific alteration minerals that serve as key indicators for mineral exploration. The Neem Ka Thana Cu Belt, situated southeast of the Khetri Cu deposit within the Alwar-Ajabgarh sub-basin of the North Delhi Fold Belt, is notable for its Bornite-rich Cu-S mineralization. Despite its geological significance, detailed spectral mapping to delineate the alteration minerals associated with base metal mineralization remained limited. This study addresses this gap by utilizing the “PRecursore IperSpettrale della Missione Applicativa” (PRISMA) hyperspectral sensor to detect and map alteration minerals associated with Cu-S mineralization.</div><div>To achieve this, we applied Relative Band Depth (RBD) indices on targeted spectral subsets of PRISMA data to identify Fe-oxides/hydroxides and Al-OH-bearing minerals. We detected key alteration minerals, including muscovite, illite, chlorite, montmorillonite and Fe-oxide and hydroxides such as goethite, hematite, and limonite, by targeting their diagnostic absorption features. The resulting spectral maps highlighting the spatial distribution of the targeted mineral groups were validated with field investigations and laboratory assessments. The study demonstrates that the integration of hyperspectral analysis with conventional geological techniques can help to understand the mineral distribution and associated alteration processes. The use of PRISMA hyperspectral data provides a powerful, non-invasive means for reconnaissance mapping of exposed lithologies, delivering targeted information that is crucial for optimizing subsequent field investigations and drilling operations. The present work highlights the potential of PRISMA data in advancing the methodologies of mineral exploration and lithological mapping, contributing valuable insights for the geoscientific community.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101421"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An examination of GNSS positioning under dense conifer forest canopy in the Pacific Northwest, USA","authors":"Jacob L. Strunk ,&nbsp;Stephen E. Reutebuch ,&nbsp;Robert J. McGaughey ,&nbsp;Hans-Erik Andersen","doi":"10.1016/j.rsase.2024.101428","DOIUrl":"10.1016/j.rsase.2024.101428","url":null,"abstract":"<div><div>Accurate positioning in the forest (e.g., less than 1–2 m horizontal error) is needed to leverage the potential of high-resolution auxiliary data sources such as airborne or satellite imagery, lidar, and photogrammetric heights used in forest monitoring. Unfortunately, typical short duration occupations in the forest with budget Global Navigation Satellite System (GNSS; GPS is the American constellation) receivers are generally inaccurate (horizontal errors &gt;5–20 m). This study demonstrates that accurate GNSS positioning is feasible beneath 40 to 60 m-tall closed-canopy conifer forests of western Washington state, USA by using survey-grade receivers with at least 15-min occupations. We also demonstrate the effects of receiver height, occupation duration, base-station distance, and differential post-processing modes (e.g., autonomous, code, fixed-integer, and floating-point) on horizontal positioning accuracies in the forest.</div><div>A geodetic survey was our benchmark for accuracy estimation but is difficult to replicate by most other GNSS users in the forest. The difficulty in setting up a geodetic survey has led to common usage of naïve accuracy estimators based on within-occupation coordinate variation (e.g., the “accuracy” reported on the face of a handheld GNSS device). In this study we demonstrate the efficacy of two simple alternatives that outperform the naïve estimator; the naïve esimator was shown to perform poorly.</div><div>The findings in this study on GNSS performance and positioning accuracy estimation supports more effective use of GNSS technology in applications that require high-performance GNSS positioning in the forest.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101428"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MultiGO: An unsupervised approach based on multi-objective growth optimizer for hyperspectral image band selection","authors":"Mohammed Abdulmajeed Moharram,&nbsp;Divya Meena Sundaram","doi":"10.1016/j.rsase.2024.101424","DOIUrl":"10.1016/j.rsase.2024.101424","url":null,"abstract":"<div><div>Hyperspectral imaging (HSI) plays a crucial role in extracting discriminative spectral-spatial features for accurate land cover classification. However, HSI datasets often suffer from the presence of irrelevant and redundant spectral bands, leading to the Hughes phenomenon and increased computational complexity. To address this challenge, this paper proposes an unsupervised approach based on the multi-objective growth optimizer for hyperspectral image dimensionality reduction. The proposed method leverages the learning phase and reflection phase of the growth optimizer to balance exploration and exploitation strategies. By incorporating information richness, reducing redundancy, and considering spatial features, the growth optimizer selects the most informative and significant spectral bands. The approach simultaneously optimizes three objective functions using the growth optimizer, creating trade-offs among them. Extensive results demonstrate the effectiveness and superiority of the proposed method in achieving dimensionality reduction and preserving the essential information in hyperspectral images. Ultimately, four machine learning classifiers, namely support vector machine, random forest, K-Nearest Neighbors, and decision tree, are applied at the pixel level for hyperspectral image classification. Moreover, the proposed method shows a significant improvement compared with five state-of-the-art techniques (bat algorithm, archimedes optimization algorithm, particle swarm optimization, harmony search, and genetic algorithm), with overall accuracy equal to 80.95 %, 92.63 %, and 90.30 % on three benchmark hyperspectral datasets namely Indian Pines, Pavia University, and Botswana, respectively.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101424"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Temporal trends and future projections: Analysing land surface temperature in the Kumaun Himalayas using spatial time series analysis","authors":"Zainab Khan ,&nbsp;Sk Ajim Ali ,&nbsp;Ateeque Ahmad ,&nbsp;Syed Kausar Shamim","doi":"10.1016/j.rsase.2024.101426","DOIUrl":"10.1016/j.rsase.2024.101426","url":null,"abstract":"<div><div>In this ground-breaking study, we introduced a novel approach for projecting Land Surface Temperature (LST) in the Kumaun Himalayas, an area critical for understanding regional impacts of global warming. The novelty of this study lies in the utilization of spatial time series analysis, a method that not previously applied for future LST prediction. In this study we examined LST trends from 1990 to 2020 and predicted LST for the year 2030 using satellite-based remote sensing data for LST estimation, advanced statistical techniques such as the Simple Moving Average (SMA), Sen's Slope, and z-statistics with excellent statistical power. The application of z-statistics provides a robust framework for assessing temperature changes, with significant findings such as a z-statistics value of −15.04 for spring, indicating a marked shift in temperature patterns. Similarly, for autumn, the z-statistics value of −21.41 underscores a drastic deviation from historical norms i.e., from 1990 to 2020. Pearson's correlation and the coefficient of determination were used to validate the accuracy of satellite-based LST estimates and SMA. A correlation of 0.93 and R² of 0.87 were found between observed and estimated LSTs, while the SMA-based LST showed a correlation of 0.92 with estimated LST with R² of 0.85. The results highlight a future that is significantly warmer than the present, bringing into sharp focus the urgency of climate change mitigation and adaptation strategies in this ecologically sensitive region. The study also suggested differential rate of seasonal warming. The study is not only pivotal for local climate policy but also contribute significantly to the broader understanding of climate dynamics in mountainous terrains is seasonal variation in warming rates. Despite challenges like rugged terrain and variable cloud cover affecting data accuracy, our approach offered a scalable model for similar climatic studies in other regions, marking a significant advancement in the field of climate change.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101426"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved radar vegetation water content integration for SMAP soil moisture retrieval","authors":"Jyoti Sharma ,&nbsp;Rajendra Prasad ,&nbsp;Prashant K. Srivastava ,&nbsp;Shubham K. Singh ,&nbsp;Suraj A. Yadav ,&nbsp;Dharmendra K. Pandey","doi":"10.1016/j.rsase.2024.101443","DOIUrl":"10.1016/j.rsase.2024.101443","url":null,"abstract":"<div><div>The Vegetation Water Content (VWC) serves as a crucial parameter within the framework of the Soil Moisture Active Passive (SMAP) satellite mission, particularly in its utilization for vegetation optical depth estimation in the Single Channel Algorithm (SCA) to determine soil moisture content. This study attempts to enhance the soil moisture estimation by estimating microwave VWC utilizing the Single Look Complex (SLC) format of dual-polarized Sentinel-1 data. This approach aims to refine the efficacy of the Single Channel Algorithm (SCA), thereby elevating the precision and reliability of soil moisture estimations. The Sentinel-1 datasets have been utilized to compute radar indices, particularly the Dual Polarimetric Radar Vegetation Index (DPRVI), Radar Vegetation Index (RVI), and Cross- and Co-Polarized Ratio (CCR). DPRVI reflects vegetation's growth and moisture properties, while RVI and CCR indicate vegetation water content and health status. The radar indices were employed within regression approaches such as random forest (RF), support vector regression (SVR), adaptive neuro-fuzzy inference system (ANFIS), and linear regression to estimate VWC. The performance of DPRVI was found better to capture aspects of vegetation dynamics and effectively estimates VWC values with a high correlation (R2) of 0.59. Furthermore, the DPRVI-estimated VWC values are integrated into the SCA, a renowned method for soil moisture retrieval. The results of SCA are compared to the ground-measured soil moisture along with the already available SMAP L2-enhanced passive soil moisture product. The soil moisture estimation via SCA integrated with the DPRVI-estimated VWC enhances the soil moisture estimations with an accuracy of (RMSE = 0.042 m³/m³ and ubRMSE = 0.039 m³/m³) compared to the SMAP L2 soil moisture. This integration allows for a more comprehensive understanding of soil-vegetation-atmosphere interactions and improves the accuracy of soil moisture assessments, critical for hydrological modeling, agricultural management, and environmental monitoring efforts.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101443"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143091896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A review on remote-sensing-based harmful cyanobacterial bloom monitoring services","authors":"Nasim Janatian ,&nbsp;Urmas Raudsepp ,&nbsp;Parya Broomandi ,&nbsp;Kate Fickas ,&nbsp;Kalle Olli ,&nbsp;Timo Heimovaara ,&nbsp;Aarne Mannik ,&nbsp;Rivo Uiboupin ,&nbsp;Nima Pahlevan","doi":"10.1016/j.rsase.2025.101488","DOIUrl":"10.1016/j.rsase.2025.101488","url":null,"abstract":"<div><div>Optical satellite observations have been recently introduced as the backbone of several harmful algal bloom monitoring frameworks for regional or continental-scale decision-making. Documented in prior peer-reviewed publications, these satellite-based decision support systems are not directly comparable, making a synthesis effort inevitable for future improvements. This review highlights select, widely used harmul cyanobacteria bloom (cyanoHABs) monitoring services, including the Cyanobacteria Assessment Network (CyAN), Cyanobacterial Bloom Indicator (CyaBI), CyanoTRACKER, EOLakeWatch, and CyanoKhoj, by focusing on their effectiveness in freshwater and inland waters. We selected these systems for their widespread use, documented effectiveness, and diverse approaches to cyanoHABs monitoring. These services provide early warnings and actionable insights, enabling effective responses to protect water quality, ecosystem health, and public safety. It considers the broader remote-sensing-based monitoring landscape, noting the capabilities and impacts of these services. Our assessments underscore the transformative impact of services like CyAN, which provide robust early warnings using the Cyanobacteria Index (CI). CyanoTRACKER and EOLakeWatch improve community engagement and data collection, increasing monitoring effectiveness. CyanoKhoj leverages high-resolution monitoring through GEE, offering valuable insights. The quality of cyanoHABs products depends on satellite imagery and processing level, noting that most processors leverage Top of Atmosphere or Rayleigh-corrected reflectance products to arrive at cyanoHABs products. Challenges in cyanoHABs monitoring also include variability in ecosystems and accurate biomass estimations. Despite challenges, services like CyAN, CyanoTRACKER, EOLakeWatch, and CyanoKhoj have made significant strides in communicating and managing cyanoHABs risks. This review <u>identifies key future research directions</u>: (1) improving algorithmic approaches and accuracy, (2) defining a universal threshold for bloom formation, (3) utilizing emerging technologies and democratizing data and information, and (4) addressing satellite technique trade-offs in cyanoHABs analysis. By focusing on these areas and <u>leveraging machine learning</u>, future advancements promise more accurate and comprehensive monitoring to protect aquatic ecosystems and public health.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101488"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143444801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}