Remote Sensing Applications-Society and Environment最新文献

{"title":"UAV visual imagery-based evaluation of blue carbon as seagrass beds on a tidal flat scale","authors":"Takuya Akinaga ,&nbsp;Mitsuyo Saito ,&nbsp;Shin-ichi Onodera ,&nbsp;Fujio Hyodo","doi":"10.1016/j.rsase.2024.101430","DOIUrl":"10.1016/j.rsase.2024.101430","url":null,"abstract":"<div><div>Seagrass and seaweed beds (SSBs) have a high carbon sequestration function (blue carbon) in shallow coastal waters. Unmanned aerial vehicles (UAVs) are a highly useful tool for monitoring SSBs because of their ease of use and ability to acquire high-resolution photographs. In many previous studies using UAV, surveys of SSBs have been based on area alone, but it is insufficient to properly assess the habitat and carbon fixation of SSBs.</div><div>In this study, we estimated above-ground biomass and carbon of eelgrass in shallow coastal waters by combining aerial photography of visible images, quadrat surveys, and sampling of eelgrass. The analysis area was a tidal flat on an island located in the Seto Inland Sea in western Japan. Aerial photography was conducted by UAV to acquire high-resolution RGB visual images of the area. The quadrat survey and sampling were used to develop regression formulas for estimating biomass and carbon of eelgrass. The former was conducted to investigate the relationship between the coverage and Leaf Area Index (LAI), and the latter was conducted to investigate the relationship between leaf area and biomass, carbon of eelgrass. Those showed clear relationship between coverage and LAI (R² = 0.97) and between leaf area and biomass, carbon (biomass: R² = 0.98, carbon: R² = 0.98).</div><div>To identify eelgrass beds, the maximum likelihood classification was adapted. After calculating the coverage from the distribution, biomass and carbon were estimated by adapting regression formulas developed by quadrat survey and sampling.</div><div>The proposed method can be easily adapted from visible images taken by UAVs and robust to the effects of water, which provides high adaptability regarding the estimation for biomass and carbon of eelgrass on the tidal flat.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101430"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092326","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}

{"title":"Enhancing earth target classification in hyperspectral imagery using graph convolutional neural networks and graph-regularized sparse coding","authors":"Geetha T S ,&nbsp;Chellaswamy C ,&nbsp;Kaliraja T ,&nbsp;Ramachandra Reddy K","doi":"10.1016/j.rsase.2024.101419","DOIUrl":"10.1016/j.rsase.2024.101419","url":null,"abstract":"<div><div>As hyperspectral remote sensing technology continues to advance, classification approaches using hyperspectral images (HSIs) have become increasingly important in earth target identification, mineral mapping, and environmental management. The strength of HSIs lies in their capacity to provide a detailed understanding of a target's composition. However, challenges such as high dimensionality, redundancy in HSI datasets, and potential class imbalances complicate their effective utilization. In this study, a novel framework combining graph convolutional neural networks (GCNNs) and graph-regularized sparse coding (GSC), referred to as GCNN-GSC, is proposed to address these challenges in HSI-based earth target classification. HSIs often exhibit irregular spatial structures, making traditional grid-based methods less effective. GCNNs excel in handling irregular grids, making them well-suited for hyperspectral data where spatial pixel arrangements deviate from regular patterns. GSC complements GCNNs by mitigating high dimensionality through compact and informative feature representation. To evaluate the efficacy of the proposed approach, a comparative study was conducted using key performance metrics, including overall accuracy, per-class accuracy, and Cohen's Kappa coefficient. The results demonstrate that GCNN-GSC outperforms state-of-the-art methods, achieving notable improvements across multiple benchmark datasets. Specifically, for the Indian Pines dataset, GCNN-GSC achieved increases of 5.74%, 5.49%, and 7.89% in Cohen's Kappa coefficient, per-class accuracy, and overall accuracy, respectively. Similar enhancements were observed for the Kennedy Space Center, Pavia University, and Houston 2013 datasets, with respective improvements of 6.58%, 6.55%, and 6.15% in Cohen's Kappa coefficient; 6.24%, 6.30%, and 5.57% in per-class accuracy; and 6.24%, 6.54%, and 6.30% in overall accuracy. These results underscore the robustness and effectiveness of GCNN-GSC in hyperspectral image classification tasks.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101419"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092434","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":"Evaluation of support vector machine classifiers for lithological mapping using PRISMA hyperspectral remote sensing data: Sahand–Bazman magmatic arc, central Iran","authors":"Naer Rahmani ,&nbsp;Milad Sekandari ,&nbsp;Amin Beiranvand Pour ,&nbsp;Hojjatollah Ranjbar ,&nbsp;Hossein Nezamabadi pour ,&nbsp;Emmanuel John M. Carranza","doi":"10.1016/j.rsase.2025.101449","DOIUrl":"10.1016/j.rsase.2025.101449","url":null,"abstract":"<div><div>Mineral exploration is highly dependent on an accurate lithological map of a study area, which provides comprehensive information on geologic features for exploration target zones. Nowadays, the processing of hyperspectral image data for lithological mapping and mineral exploration using machine learning (ML) algorithms has greatly developed. The recently launched Italian hyperspectral sensor ‘PRecursore IperSpettrale della Missione Applicativa (PRISMA)’ offers an excellent capability for mineral detection and object classification with superior accuracy and efficiency for lithological mapping and mineral exploration. In this study, the performance of the support vector machine (SVM) algorithm was evaluated for processing PRISMA datasets to generate lithological maps of the Sar Cheshmeh porphyritic copper ore deposit in the Sahand–Bazman magmatic arc in central Iran. Three different SVM kernels, namely linear (LSVM), quadratic (QSVM) and cubic (CSVM), were comparatively evaluated for data classification in lithological mapping. The SVM classifiers were trained on the basis of prior knowledge from previous studies and field surveys. Approximately 5000 pixels from 14 different classes were used for training. There was a large misclassification between granodiorites and altered granodiorites in the LSVM result (78.3% accuracy for altered granodiorites), but this was greatly reduced in the QSVM and CSVM methods (with 96.1% and 99.1% accuracy, respectively). A significant improvement in classification was also seen for the vegetation, mine pits and Razak volcanism classes (with varying accuracy values). It is noteworthy that nine of the 14 classes had less than 400 training pixels and only one class had more than 1000 pixels used for training, indicating the power of ML for such studies. LSVM was the best method for mapping dacites with maximum accuracy (100%), but this accuracy was slightly lower for QSVM and CSVM (both had 97.9% accuracy). The results show that the LSVM, QSVM and CSVM methods achieved an accuracy of 80.22%, 85.81% and 86.05%, respectively, in the final classification. This study advocates the optimal SVM classifier (CSVM classifier) using PRISMA hyperspectral images for accurate lithological mapping for mineral exploration in metallogenic provinces.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101449"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092438","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":"Remote sensing measurements of fresh volcanic ash during the Mount Etna emission of February 21, 2019","authors":"Salvatore Spinosa ,&nbsp;Antonella Boselli ,&nbsp;Luigi Mereu ,&nbsp;Giuseppe Leto ,&nbsp;Ricardo Zanmar Sanchez ,&nbsp;Simona Scollo","doi":"10.1016/j.rsase.2024.101413","DOIUrl":"10.1016/j.rsase.2024.101413","url":null,"abstract":"<div><div>Explosive activity can have a relevant impact in the atmosphere even during weak and continuous volcanic ash emissions. In fact, this type of activity can affect highly populated areas and needs to be investigated in order to reduce potential risks. In this paper, we analyze the volcanic ash emissions that took place on February 21, 2019 from the North East Crater, one of the summit craters of Mount Etna, in Italy. During the activity, a continuous ash emission caused the closure of the International Airport in Catania due to a large quantity of volcanic particles in the atmosphere that were dispersed by winds several kilometers away from the eruptive crater, mainly toward the west, south and south-east directions. This activity was analyzed using a dual depolarization LiDAR and visual and thermal cameras that are part of the instrumental network of the Istituto Nazionale di Geofisica e Vulcanologia, Osservatorio Etneo. The LiDAR derived aerosol backscattering coefficient and particle linear depolarization ratio profiles, both measured at 355 nm and 532 nm, gave insights on plume dynamics and variations of some features of the particles within the volcanic plume. During this event, we estimated a maximum volcanic plume height of about 3 km above sea level and LiDAR data show two distinct layers in the atmosphere, LiDAR derived aerosol properties were used for a first application of the Volcanic Ash LiDAR Retrieval - Maximum Likelihood (VALR-ML) algorithm on two volcanic ash layers, allowing to obtain a maximum value of volcanic ash concentration of 7.5 ± 3.7 mg/m³ and 8.1 ± 4.0 mg/m³, in the first layer at 355 and 532 nm, respectively; while in the second layer we obtained concentration values of 6.6 ± 3.3 and 8.5 ± 4.2 mg/m³ at 355 and 532 nm, respectively. Moreover, the plume was composed of very fine ash of about 1 μm dimensions. We found that weak and continuous volcanic ash emissions can reach thresholds that cause troubles to aviation operations. Our work shows how LiDAR systems are able to estimate critical information for aviation safety in the proximity of the airport, such as the altitude, the concentration and the size of emitted ash particles, even during low-intensity explosive activity.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101413"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143125466","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}

{"title":"An improved radiative transfer inversion of physical temperatures in Antarctic ice sheet using SMOS observations","authors":"Yi Zhou ,&nbsp;Yongjiu Feng ,&nbsp;Yuze Cao ,&nbsp;Shurui Chen ,&nbsp;Zhenkun Lei ,&nbsp;Mengrong Xi ,&nbsp;Jingbo Sun ,&nbsp;Yuhao Wang ,&nbsp;Tong Hao ,&nbsp;Xiaohua Tong","doi":"10.1016/j.rsase.2025.101487","DOIUrl":"10.1016/j.rsase.2025.101487","url":null,"abstract":"<div><div>The internal temperature plays a pivotal role in dictating the dynamics and thermal processes of the Antarctic ice sheet. Low-frequency microwave remote sensing methods show promise for effectively gauging the ice sheet's deep glaciological properties. Our study leverages brightness temperature data at L-band (1.4 GHz) from the Soil Moisture and Ocean Salinity (SMOS) satellite, integrating it with glaciological thermodynamic and radiative transfer models to infer the ice sheet's internal temperature. We fine-tune the geothermal heat flux and snow accumulation rate parameters using the Generalized Simulated Annealing (GSA) algorithm. Our findings reveal that this methodology, compared to estimations grounded on prior knowledge, diminishes the Root Mean Square Error (RMSE) for brightness temperature inversion by roughly 3 K. Further, the RMSE for the physically inverted temperature profile, when benchmarked against ice core drilling data from Dome C and Dome Fuji, stands at 1.55 K and 1.36 K, respectively. This approach narrows the uncertainty in assessing the Antarctic ice sheet's temperature profile, particularly within the upper 2000 m. Accurately determined physical temperatures within the ice sheet enhance our comprehension of its intricate thermal structure. We anticipate that these insights should provide valuable scientific input for addressing concerns related to the ice sheet's mass balance and evolutionary processes.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101487"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143428054","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":"Analysis of asbestos-cement roof classification in urban areas: Supervised and unsupervised methods with multispectral and hyperspectral remote sensing","authors":"Manuel Saba ,&nbsp;Carlos Castrillón-Ortíz ,&nbsp;David Valdelamar-Martínez ,&nbsp;Oscar E. Coronado-Hernández ,&nbsp;Ciro Bustillo-LeCompte","doi":"10.1016/j.rsase.2025.101464","DOIUrl":"10.1016/j.rsase.2025.101464","url":null,"abstract":"<div><div>Asbestos-cement roofs, commonly found in urban areas, pose environmental and health risks as they deteriorate, releasing asbestos fibres into the atmosphere. Accurate identification and classification of these roofs are essential for assessing potential hazards and implementing appropriate remediation measures. This study presents a comprehensive analysis of supervised and unsupervised classification methods for the identification of asbestos-cement roofs in an urban area using both multispectral and hyperspectral remote sensing data. Six well-established supervised classification methods and two unsupervised classification methods were employed to analyse multispectral (WorldView 3 satellite) and hyperspectral data (overflight), offering ground pixel resolutions of 3.7 m and 1.2 m for both images. ENVI® was utilized for classification purposes. The supervised methods included in the study were Parallelepiped (PP), Minimum Distance (MiD), Mahalanobis Distance (MhD), Spectral Angle Mapper (SAM), Support Vector Machine (SVM) and Spectral Information Divergence (SID). In contrast, unsupervised methods were K-Means and ISO-Data. The classification performance of each method was assessed based on several metrics. The novelty of this study lies in the first-ever comparison of six supervised and two unsupervised methods applied to hyperspectral imagery captured via aerial survey and satellite imagery over the same urban area. Results indicate that hyperspectral data outperformed multispectral data in terms of asbestos-cement roof classification, demonstrating the potential of hyperspectral imagery for more precise identification. Additionally, the supervised classifiers consistently outperformed the unsupervised methods, highlighting the importance of a priori knowledge for accurate classification. In contrast, the cost-benefit analysis reveals that multispectral imagery is significantly more cost-efficient, being up to 6.5 times less expensive and requiring approximately 32 times fewer computational resources than hyperspectral imagery. This study provides important insights for urban planning, environmental assessment, and public health management by enabling accurate and efficient identification of asbestos-cement roofs in urban areas. The findings highlight the critical role of selecting appropriate remote sensing data and classification techniques for such applications. The methodology and results offer valuable guidance to local authorities, researchers, and policymakers in addressing asbestos-related risks, particularly in developing countries confronting these challenges.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101464"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143349348","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}

{"title":"First thermographic survey within the Euganean thermal district (Italy) with an unmanned aerial vehicle","authors":"Luca Peruzzo ,&nbsp;Andrea Berton ,&nbsp;Michele Crivellaro ,&nbsp;Cristina Da Lio ,&nbsp;Sandra Donnici ,&nbsp;Paolo Fabbri ,&nbsp;Gian Marco Scarpa ,&nbsp;Fabio Tateo ,&nbsp;Luca Zaggia ,&nbsp;Andrea Fasson","doi":"10.1016/j.rsase.2024.101431","DOIUrl":"10.1016/j.rsase.2024.101431","url":null,"abstract":"<div><div>The territory of the Euganean Hills is known worldwide for the occurrence of thermal springs known since ancient times. Currently, local authorities greatly enhance the natural capital of the Hills, including the thermal waters. Despite all this, remote thermal sensing has never been performed before and the present work aims to fill this gap. For this purpose, an UAV survey was conducted in a selected area, accompanied by ground measurements of water temperature and conductivity. The thermographic survey identified known and unknown thermal springs, as well as water leaks from greenhouses and abandoned wells. Since the thermal water is both hot and salty, the UAV system is able to detect the points where salt water is introduced into the fresh water network used for irrigation purposes. Ground controls have made it possible to trace the mixing process between these two types of water, salty (of thermal origin) and fresh (suitable for agriculture) over wider distances and with greater precision. Climate changes and the variable exploitation of water resources cause the continuous change in the balance between salt thermal and fresh water. Therefore, a strong salinization of the water in the surface network can occur as has been documented within the area under examination, also causing severe damage to agriculture. The thermographic survey, accompanied by in situ measurements, proved to be a very effective system for the management of a highly vulnerable territory as observed in the Euganean Hills.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101431"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092430","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}

{"title":"What time is the tide? The importance of tides for ocean colour applications to estuaries","authors":"Giulia Sent ,&nbsp;Carlos Antunes ,&nbsp;Evangelos Spyrakos ,&nbsp;Thomas Jackson ,&nbsp;Elizabeth C. Atwood ,&nbsp;Ana C. Brito","doi":"10.1016/j.rsase.2024.101425","DOIUrl":"10.1016/j.rsase.2024.101425","url":null,"abstract":"<div><div>Tides can play a major role in transitional water dynamics, being the primary driver of fluctuations in water parameters. In the last decade, remote sensing methods have become a popular tool for cost-effective systematic observations, at relatively high spatial and temporal scales. However, the presence of tides introduces complexities, given that Sun-synchronous satellites will observe a different tidal condition at each overpass, effectively aliasing the daily signal. This can create non-obvious biases when using remote sensing data for monitoring tidally-dominated systems, potentially leading to misinterpretation of patterns and incorrect estimates of periodicities. In this work, we used a six-year Sentinel-2-derived turbidity dataset to evaluate the impact of tidal aliasing on the applicability of a Sun-synchronous satellite to a tidally-dominated system (Tagus estuary, Portugal). Each satellite observation was classified according to tidal phase. Results indicate that tidal processes dominated over seasonal variability, with significant differences observed between turbidity levels of different tidal phases (p &lt; 0.0001). Climatology analyses also revealed significant changes between all-data and per-tidal-phase data (p &lt; 0.001), highlighting the importance of classifying satellite data by tidal condition. Additionally, tidal condition labelling at each Sentinel-2 overpass revealed that not all tidal conditions are observed by a Sun-synchronous satellite, as Low tide and Floods are always observed during Spring tides and High tide and Ebbs observed under Neap tides. Spring Low tides are overrepresented compared to all other tidal conditions. This result is particularly relevant for water quality monitoring based on remote sensing data in tidally-dominated systems.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101425"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092433","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}

{"title":"SimPoolFormer: A two-stream vision transformer for hyperspectral image classification","authors":"Swalpa Kumar Roy ,&nbsp;Ali Jamali ,&nbsp;Jocelyn Chanussot ,&nbsp;Pedram Ghamisi ,&nbsp;Ebrahim Ghaderpour ,&nbsp;Himan Shahabi","doi":"10.1016/j.rsase.2025.101478","DOIUrl":"10.1016/j.rsase.2025.101478","url":null,"abstract":"<div><div>The ability of vision transformers (ViTs) to accurately model global dependencies has completely changed the field of vision research. However, because of their drawbacks, such as their high computational costs, dependence on significant labeled datasets, and restricted capacity to capture essential local features, efforts are being made to create more effective alternatives. On the other hand, vision multilayer perceptron (MLP) architectures have shown excellent capability in image classification tasks, performing equivalent to or even better than the widely used state-of-the-art ViTs and convolutional neural networks (CNNs). Vision MLPs have linear computational complexity, require less training data, and can attain long-range data dependencies through advanced mechanisms similar to transformers at much lower computational costs. Thus, in this paper, a novel deep learning architecture is developed, namely, SimPoolFormer, to address current shortcomings imposed by vision transformers. SimPoolFormer is a two-stream attention-in-attention vision transformer architecture based on two computationally efficient networks. The developed architecture replaces the computationally intensive multi-headed self-attention in ViT with SimPool for efficiency, while ResMLP is adopted in a second stream to enhance hyperspectral image (HSI) classification, leveraging its linear attention-based design. Results illustrate that SimPoolFormer is significantly superior to several other deep learning models, including 1D-CNN, 2D-CNN, RNN, VGG-16, EfficientNet, ResNet-50, and ViT on three complex HSI datasets: QUH-Tangdaowan, QUH-Qingyun, and QUH-Pingan. For example, in terms of average accuracy, SimPoolFormer improved the HSI classification accuracy over 2D-CNN, VGG-16, EfficientNet, ViT, ResNet-50, RNN, and 1D-CNN by 0.98%, 3.81%, 4.16%, 7.94%, 9.45%, 12.25%, and 13.95%, respectively, on the QUH-Qingyun dataset.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101478"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143128314","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":"Mapping built infrastructure in semi-arid systems using data integration and open-source approaches for image classification","authors":"Megan R. Dolman ,&nbsp;Nicholas E. Kolarik ,&nbsp;T. Trevor Caughlin ,&nbsp;Jodi S. Brandt ,&nbsp;Rebecca L. Som Castellano ,&nbsp;Megan E. Cattau","doi":"10.1016/j.rsase.2025.101472","DOIUrl":"10.1016/j.rsase.2025.101472","url":null,"abstract":"<div><div>Accurate land use land cover (LULC) maps that delineate built infrastructure are useful for numerous applications, from urban planning, humanitarian response, disaster management, to informing decision making for reducing human exposure to natural hazards, such as wildfire. Existing products lack sufficient spatial, temporal, and thematic resolution, omitting critical information needed to capture LULC trends accurately over time. Advancements in remote sensing imagery, open-source software and cloud computing offer opportunities to address these challenges. Using Google Earth Engine, we developed a novel built infrastructure detection method in semi-arid systems by applying a random forest classifier to a fusion of Sentinel-1 and Sentinel-2 time series. Our classifier performed well, differentiating three built environment types: residential, infrastructure, and paved, with overall accuracies ranging from 90 to 96%. Producer accuracies were highest for the infrastructure class (98–99%), followed by the residential class (91–96%). Sentinel-1 variables were important for differentiating built classes. We illustrated the utility of our mapped products by generating a time-series of change across southern Idaho spanning 2015 to 2024 and comparing this with publicly available products: National Land Cover Database (NLCD), Microsoft Building Footprints (MBF) and the global Dynamic World (DW). For 2024, our product estimated 5.88% of the study area as built, aligning closely with NLCD (6%) and DW (4.64%). Our mapped built infrastructure products offer enhancements over NLCD spatially and temporally, over DW thematically, and over MBF both temporally and thematically. We demonstrate the potential of fusing data sources to improve LULC mapping and present a case for regionally parameterized models that can more accurately capture built infrastructure change over time. We used open-source approaches for built infrastructure detection, aiming for broader adoption of this workflow across other ecosystems and environments to support decision-making.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101472"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143091902","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}