Remote Sensing Research Articles

Predictive Modelling of Mineral Prospectivity Using Satellite Remote Sensing and Machine Learning Algorithms

In today’s world of falling returns on fixed exploration budgets, complex targets, and ever-increasing volumes of multi-parameter datasets, the effective management and integration of existing data are essential to any mineral exploration operation. Machine learning (ML) algorithms like Convolutional Neural Networks (CNN), Random Forest (RF), and Support Vector Machine (SVM) are powerful data-driven methods that are not implemented very often with remote sensing-derived hydrothermal alternation information and limited field datasets for mapping mineral prospectivity. The application of machine learning algorithms with satellite remote sensing data and limited field data, they have not been compared and evaluated together thoroughly in this field. A data science approach was applied to create nine predictor maps, incorporating limited field data and satellite remote sensing information. A confusion matrix, statistical measures, and a Receiver Operating Characteristic (ROC) curve were used to evaluate the prediction models efficacy on both the training and test datasets. The results suggested that the RF model exhibited the highest predictive accuracy, consistency and interpretability among the three ML models evaluated in this study. RF model also achieved the highest predictive efficiency in capturing known copper (Cu) deposits within a small prospective area. In comparison to the SVM and CNN models, the RF model outperformed them in terms of predictive accuracy and interpretability. These results imply that the RF model is the most suitable for Cu potential mapping in the Pakistan’s North Waziristan region. Consequently, all the models including the RF model were used to generate a prospectivity map, which contained low to very-high potential zones, to support further exploration in the region. The newly discovered deposit inside the predicted prospective areas demonstrates the robustness and efficacy of the prospectivity modelling approach as proposed in this research for generating exploration targets.

Flood Detection and Monitoring using IOT

One of the most destroying characteristic pf natures that can happen any place in the globe is flooding. In consideration to keep an eye on the surge circumstance particularly in a low line range, a framework was put and developed to track the Dam water level, Door opening status and precipitation level in real-time. A application-based data source for the open, reacting to their require for data on water conditions and flooding, and a Status page for data approximately flooding between the included specialists and specialists to move forward their obligations and participation are the two essential objectives of the made framework. A sensor organizes, a processing/transmission unit, and a database/application server make up the made framework. With the offer assistance of a remote sensor arrange that communicates with the application server over versatile Common Parcel Radio Benefit (GPRS), it is conceivable to remotely screen this real-time information of water condition. To encourage communication between the application server a microcontroller will be utilized. Ultrasonic sensors will be utilized to bring the correct level of the water in the dam. The entryway opening status will be picked up through a few sensors like water sensors and rain sensors. The versatile application which is made and associated with a few IOT Sensors will be having two major segments i.e. Flood Status and Emergency services. A few crisis administrations like healing centres, transport will be included in this application which will be valuable in the overwhelmed circumstances and post overflowed circumstances.

Predictive Modelling of Land Cover Changes in the Greater Amanzule Peatlands Using Multi-Source Remote Sensing and Machine Learning Techniques

The Greater Amanzule Peatlands (GAP) in Ghana is an important biodiversity hotspot facing increasing pressure from anthropogenic land-use activities driven by rapid agricultural plantation expansion, urbanisation, and the burgeoning oil and gas industry. Accurate measurement of how these pressures alter land cover over time, along with the projection of future changes, is crucial for sustainable management. This study aims to analyse these changes from 2010 to 2020 and predict future scenarios up to 2040 using multi-source remote sensing and machine learning techniques. Optical, radar, and topographical remote sensing data from Landsat-7, Landsat-8, ALOS/PALSAR, and Shuttle Radar Topography Mission derived digital elevation models (DEMs) were integrated to perform land cover change analysis using Random Forest (RF), while Cellular Automata Artificial Neural Networks (CA-ANNs) were employed for predictive modelling. The classification model achieved overall accuracies of 93% in 2010 and 94% in both 2015 and 2020, with weighted F1 scores of 80.0%, 75.8%, and 75.7%, respectively. Validation of the predictive model yielded a Kappa value of 0.70, with an overall accuracy rate of 80%, ensuring reliable spatial predictions of future land cover dynamics. Findings reveal a 12% expansion in peatland cover, equivalent to approximately 6570 ± 308.59 hectares, despite declines in specific peatland types. Concurrently, anthropogenic land uses have increased, evidenced by an 85% rise in rubber plantations (from 30,530 ± 110.96 hectares to 56,617 ± 220.90 hectares) and a 6% reduction in natural forest cover (5965 ± 353.72 hectares). Sparse vegetation, including smallholder farms, decreased by 35% from 45,064 ± 163.79 hectares to 29,424 ± 114.81 hectares. Projections for 2030 and 2040 indicate minimal changes based on current trends; however, they do not consider potential impacts from climate change, large-scale development projects, and demographic shifts, necessitating cautious interpretation. The results highlight areas of stability and vulnerability within the understudied GAP region, offering critical insights for developing targeted conservation strategies. Additionally, the methodological framework, which combines optical, radar, and topographical data with machine learning, provides a robust approach for accurate and detailed landscape-scale monitoring of tropical peatlands that is applicable to other regions facing similar environmental challenges.

Limits for the Identification of Smectites Mixed with Common Minerals Based on Short-Wave Infrared Spectroscopy

The identification of minerals, particularly clay minerals, using visible, near-infrared, and short-wave infrared (VNIR-SWIR) spectroscopy has gained prominence due to its efficiency and the advancement of remote hyperspectral sensors. However, identifying minerals in polymineralic samples remains challenging due to overlapping absorption features. This study prepared systematic binary mixtures of two smectites (dioctahedral and trioctahedral) with common non-clay minerals (calcite, dolomite, gypsum, quartz, and feldspar). Spectra from these mixtures were obtained using the ASD FieldSpec 4 Hi-Res spectroradiometer and analyzed with continuum removal and second derivative preprocessing to define detection limits. These limits indicate the minimum percentage of each mineral required for clear identification in various smectite–non-clay combinations. After continuum removal, smectites are identified at ≥5%–10% in mixtures with carbonates, quartz, and feldspar, but ≥70% is needed for gypsum. Non-clay minerals have detection limits of ≥70% for calcite and 20% for gypsum in the presence of smectites, while dolomite remains undetectable. The second derivative improves these limits, enabling smectite identification at 5% in carbonate mixtures and 5%–15% in gypsum mixtures. Calcite detection limits are 65%, and dolomite can be identified at ≥65% and ≥85% with dioctahedral and trioctahedral smectites, respectively. Gypsum detection limits are reduced to 10%, while quartz and feldspar cannot be identified due to lacking absorption features.

EFFICIENT SCHEMES OF CLASSIFIERS FOR REMOTE SENSING SATELLITE IMAGERIES OF LAND USE PATTERN CLASSIFICATIONS

Land use pattern classification of remote sensing imagery data is imperative to research that is used in remote sensing applications. Remote sensing (RS) technologies were exploited to mine some of the significant spatially variable factors, such as land cover and land use (LCLU), from satellite images of remote arid areas in Karnataka, India. Four diverse classification techniques unsupervised, and supervised (Maximum likelihood, Mahalnobis Distance, and Minimum Distance) are applied in Bellary district in Karnataka, India for the classification of the raw satellite images. The developed maps are then visually compared with each other and accuracy evaluations make using of ground-truths are carried out. It was initiated that the Maximum likelihood technique gave the finest results and both Minimum distance and Mahalnobis distance methods overvalued agricultural land areas. In spite of missing a few insignificant features due to the low resolution of the satellite images, a high-quality accord between parameters extracted automatically from the developed maps and field observations was found. Keywords: Remote sensing (RS), land cover and land use (LCLU).

Soil and Water Assessment Tool (SWAT)-Informed Deep Learning for Streamflow Forecasting with Remote Sensing and In Situ Precipitation and Discharge Observations

In order to anticipate residual errors and improve accuracy while reducing uncertainties, this work integrates the long short-term memory (LSTM) with the Soil and Water Assessment Tool (SWAT) to create a deep learning (DL) model that is guided by physics. By forecasting the residual errors of the SWAT model, the SWAT-informed LSTM model (LSTM-SWAT) differs from typical LSTM approaches that predict the streamflow directly. Through numerical tests, the performance of the LSTM-SWAT was evaluated with both LSTM-only and SWAT-only models in the Upper Heihe River Basin. The outcomes showed that the LSTM-SWAT performed better than the other models, showing higher accuracy and a lower mean absolute error (MAE = 3.13 m3/s). Sensitivity experiments further showed how the quality of the training dataset affects the performance of the LSTM-SWAT. The results of this study demonstrate how the LSTM-SWAT may improve streamflow prediction greatly by remote sensing and in situ observations. Additionally, this study emphasizes the need for detailed consideration of specific sources of uncertainty to further improve the predictive capabilities of the hybrid model.

LANDSLIDE DETECTION AND MONITORING TECHNIQUES: A BIBLIOMETRIC ANALYSIS AND FUTURE DIRECTIONS

The devastating consequences of landslides demand rigorous assessment and effective management strategies to minimise risks. In this context, landslide detection and monitoring are crucial in identifying potential hazards and implementing proactive mitigation measures. This study uses the Scopus database to present a bibliometric analysis of 1,112 peer-reviewed journal articles on landslide detection and monitoring techniques published between 2002 and 2022. The analysis reveals a remarkable surge in publications, from 4 in 2002 to 180 in 2022, with the last five years (2018-2022) accounting for over 60% of the total publications. Over 3,259 unique researchers from 75 countries contributed to this field, with a significant portion originating from Asia, Europe, and North America. China and Italy emerged as the leading countries, producing over half of the articles. Nicola Casagli, from Italy, authored the most publications and garnered the highest number of citations. Remote Sensing emerged as the most preferred journal for authors, while Landslides garnered the highest total citations, and Geomorphology has the most normalised citations per article. The Chinese Academy of Sciences, China University of Geosciences, and the University of Florence in Italy were the most productive research institutions. The Natural Science Foundation of China (NSFC) emerged as the top funding agency. “Landslide”, “landslide monitoring”, and “early warning systems” were the top three most frequently used keywords. Keyword analysis identified landslide detection and monitoring advancements in remote sensing, analytical methods, and in-situ techniques. Co-occurrence analysis of trending research terms highlighted three distinct thematic clusters: remotely sensed data with machine learning and image analysis for landslide detection, field instrumentation for continuous deformation monitoring, and development of early warning systems for landslide hazard assessment and mitigation.

A Methodological Framework for High-Resolution Surface Urban Heat Island Mapping: Integration of UAS Remote Sensing, GIS, and the Local Climate Zoning Concept

The urban heat island effect (UHI) is among the major challenges of urban climate, which is continuously intensifying its impact on urban life and functioning. Against the backdrop of increasingly prolonged heatwaves observed in recent years, practical questions about adaptation measures in cities are growing—questions that traditional meteorological monitoring can hardly answer adequately. On the other hand, UHI has long been the focus of research interest, but due to the technological complexity of providing accurate spatially referenced data at high spatial resolution and the requirement to survey at strictly defined parts of the day, information provision is becoming a major challenge. This is one of the main reasons why UHI research results are less often used directly in urban spatial planning. However, advances in geospatial technologies, including unmanned aerial systems (UASs), are providing more and more reliable tools that can be applied to achieve better and higher-quality information resources that adequately characterize the UHI phenomenon. This paper presents a developed and tested methodology for the rapid and efficient assessment and mapping of the effects of surface urban heat island (SUHI). It is entirely based on the integrated use of data from unmanned aerial systems (UAS)-based remote sensing methods, including thermal photogrammetry and GIS-based analysis methods. The study follows the understanding that correct SUHI research depends on a proper understanding of the urban geosystem, its spatial and structural heterogeneity, and its functional systems, which in turn can only be achieved by supporting the research process with accurate and reliable information resources. In this regard, the possibilities offered by the proposed methodological scheme for efficient geospatial registration of SUHI variations at the microscale, including the calculation of intra-urban SUHI intensity, are discussed in detail. The methodology builds on classical approaches for using local climate zoning (LCZ), adding capabilities for precise delineation of individual zone types and for geostatistical characterization of the urban surface heat island (SUHI). Finally, the proposed scheme is based on state-of-the-art technological tools that provide flexible and automated capabilities to investigate the phenomenon at microscales, including by enabling flexible observation of its dynamics in terms of heat wave manifestation and evolution. Results are presented from a series of sequential tests conducted on the largest residential area in Bulgaria’s capital city, Sofia, in terms of area and population, over a relatively long period from 2021 to 2024.

Remote Sensing of Residential Landscape Irrigation in Weber County, Utah: Implications for Water Conservation, Image Analysis, and Drone Applications

Analyzing irrigation patterns to promote efficient water use in urban areas is challenging. Analysis of irrigation by remote sensing (AIRS) combines multispectral aerial imagery, evapotranspiration data, and ground-truth measurements to overcome these challenges. We demonstrate AIRS on eight neighborhoods in Weber County, Utah, using 0.6 m National Agriculture Imagery Program (NAIP) and 0.07 m drone imagery, reference evapotranspiration (ET), and water use records. We calculate the difference between the actual and hypothetical water required for each parcel and compare water use over three time periods (2018, 2021, and 2023). We find that the quantity of overwatering, as well as the number of customers overwatering, is decreasing over time. AIRS provides repeatable estimates of irrigated area and irrigation demand that allow water utilities to track water user habits and landscape changes over time and, when controlling for other variables, see if water conservation efforts are effective. In terms of image analysis, we find that (1) both NAIP and drone imagery are sufficient to measure irrigated area in urban settings, (2) the selection of a threshold value for the normalized difference vegetation index (NDVI) becomes less critical for higher-resolution imagery, and (3) irrigated area measurement can be enhanced by combining NDVI with other tools such as building footprint extraction, object classification, and deep learning.

UAV REMOTE SENSING APPLICATIONS IN BEACH-CLIFF SYSTEM MONITORING OF MORPHODYNAMIC PROCESSES

This study aims to evaluate the morphodynamic changes in a beach-cliff system in northeastern Brazil using high resolution data collected by UAV-SfM techniques to understand the geomorphic changes of the coastal landscape. The study used the Geomorphic Change Detection (GCD) method applied to short-term monitoring. This method uses Digital Elevation Models (DEMs) to determine the morphological changes in terms of both erosion and deposition through DEMs of Difference (DoDs). The difference gridded models are acquired by drone-based remote sensing, which can accurately and efficiently provide ultra-high resolution imagery and digital surface model data to measure volumetric changes. The geomorphic changes are observed on high resolution maps. The multi-temporal analysis revealed significant volumes of erosion and deposition throughout the beach-cliff system over the study period. In the first interval (May/2021 - November/2021), the cliff recorded -8,715 m³ of erosion and 2,816 m³ of deposition, with the beach sector showing erosion in 86% of its area. In the second period (November/2021 - March/2022), more severe erosion rates were observed on the cliff, reaching -10,853 m³ with 51% of its area eroded, while the beach showed the opposite behavior to that previously analyzed, with 73% of the beach experiencing an accumulation of sand and a positive balance of 5,960 m³. The results of this study can be fruitful in identifying the different of geomorphology hazards, coastal impacts of cliff urbanization and in the use of remotely piloted aircraft in coastal monitoring. Furthermore, the results indicate that the management of the beach-cliff system must be integrated and never dissociated, as is generally done by coastal managers. Keywords: Geomorphometry; DEMs; Drone-Based Remote Sensing; Mass Movement; Elevation and Volumetric.

Remote Sensing–Based UAV Imaging in Heat Pattern Analysis Impact on Climate Change Detection Using Fuzzy Stacked Lasso Elastic-Net Model

Remote Sensing–Based UAV Imaging in Heat Pattern Analysis Impact on Climate Change Detection Using Fuzzy Stacked Lasso Elastic-Net Model

Ecophysiological variables retrieval and early stress detection: insights from a synthetic spatial scaling exercise

ABSTRACT The ability to access physiologically driven signals, such as surface temperature, photochemical reflectance index (PRI), and sun-induced chlorophyll fluorescence (SIF), through remote sensing (RS) are exciting developments for vegetation studies. Accessing this ecophysiological information requires considering processes operating at scales from the top-of-the-canopy to the photosystems, adding complexity compared to reflectance index-based approaches. To investigate the maturity and knowledge of the growing RS community in this area, COST Action CA17134 SENSECO organized a Spatial Scaling Challenge (SSC). Challenge participants were asked to retrieve four key ecophysiological variables for a field each of maize and wheat from a simulated field campaign: leaf area index (LAI), leaf chlorophyll content (C ab), maximum carboxylation rate (V cmax,25), and non-photochemical quenching (NPQ). The simulated campaign data included hyperspectral optical, thermal and SIF imagery, together with ground sampling of the four variables. Non-parametric methods that combined multiple spectral domains and field measurements were used most often, thereby indirectly performing the top-of-the-canopy to photosystem scaling. LAI and C ab were reliably retrieved in most cases, whereas V cmax,25 and NPQ were less accurately estimated and demanded information ancillary to RS imagery. The factors considered least by participants were the biophysical and physiological canopy vertical profiles, the spatial mismatch between RS sensors, the temporal mismatch between field sampling and RS acquisition, and measurement uncertainty. Furthermore, few participants developed NPQ maps into stress maps or provided a deeper analysis of their parameter retrievals. The SSC shows that, despite advances in statistical and physically based models, the vegetation RS community should improve how field and RS data are integrated and scaled in space and time. We expect this work will guide newcomers and support robust advances in this research field.

A Patch-Level Region-Aware Module with a Multi-Label Framework for Remote Sensing Image Captioning

Recent Transformer-based works can generate high-quality captions for remote sensing images (RSIs). However, these methods generally feed global or grid visual features to a Transformer-based captioning model for associating cross-modal information, which limits performance. In this work, we investigate unexplored ideas for a remote sensing image captioning task, using a novel patch-level region-aware module with a multi-label framework. Due to an overhead perspective and a significantly larger scale in RSIs, a patch-level region-aware module is designed to filter the redundant information in the RSI scene, which benefits the Transformer-based decoder by attaining improved image perception. Technically, the trainable multi-label classifier capitalizes on semantic features as supplementary to the region-aware features. Moreover, modeling the inner relations of inputs is essential for understanding the RSI. Thus, we introduce region-oriented attention, which associates region features and semantic labels, omits the irrelevant regions to highlight relevant regions, and learns related semantic information. Extensive qualitative and quantitative experimental results show the superiority of our approach on the RSICD, UCM-Captions, and Sydney-Captions. The code for our method will be publicly available.

Space–Ground Remote Sensor Network for Monitoring Suspended Sediments in the Yellow River Basin

The Yellow River, China’s second-largest river, is renowned for its high sediment content. In response to the potential impacts of climate change on Yellow River water resources and water environmental management, an advanced monitoring and forecasting system for water and sediment throughout the entire Yellow River basin—from its source to the sea—is urgently needed. In this paper, based on the current status of water and sediment monitoring technologies, we proposed an integrated remote sensing monitoring network that combines satellite remote sensing, drone remote sensing, and ground-based wireless automatic monitoring networks, aiming to achieve the digital monitoring of water and sediment across the entire Yellow River basin, from its upper reaches to its estuary in the Bohai Sea. By utilizing ground-based in situ hyperspectral stations for sediment source areas in the upper reaches, such as the Qingshui River basin in Ningxia, and satellite remote sensing for midstream processes in the Xiaolangdi reservoir before the flood season in 2023, as well as downstream monitoring at the Yellow River estuary, this paper demonstrates the novelty and efficiency of the space–air–ground integrated remote sensing monitoring technology.

Special Issue of Marine Geodesy on Geomatics, Remote Sensing, and Climate Change in the Arctic, Antarctica, and High Mountain Asia

Special Issue of Marine Geodesy on Geomatics, Remote Sensing, and Climate Change in the Arctic, Antarctica, and High Mountain Asia

Impact of Remote Dielectric Sensing on Predicting Worsening Heart Failure During Hospitalization for Heart Failure

Background: A remote dielectric sensing (ReDS) system quickly quantifies pulmonary congestion. Nonetheless, its efficacy in predicting an in-hospital increase in plasma B-type natriuretic peptide levels, the potential surrogate of worsening heart failure, remains undetermined. Methods: Patients who underwent ReDS measurement on admission during their hospitalization in the general wards for heart failure between 2021 and 2022 were eligible. The impact of the baseline ReDS value, completely blinded to the attending clinicians, on the in-hospital increase in plasma B-type natriuretic peptide levels of >100 pg/mL from index admission was evaluated. Results: A total of 147 patients admitted with acute-on-chronic heart failure (median age: 79 years; 76 men) were included. The median ReDS value on admission was 28% (25%, 34%). Eighteen patients experienced the primary outcome: plasma B-type natriuretic peptide levels increasing from 461 (207, 790) pg/mL (baseline) to 958 (584, 1290) pg/mL (maximum) (p < 0.001). The ReDS value on admission was an independent predictor of the primary outcome, with an adjusted odds ratio of 1.07 (95% confidence interval: 1.01–1.14; p = 0.028) with an optimal cutoff of 32%. Conclusions: The ReDS system could be a promising tool for predicting in-hospital worsening heart failure in patients hospitalized for heart failure when measured upon admission. The clinical implication of ReDS-guided management of heart failure during index hospitalization requires further studies.

Potential Sites for Rainwater Harvesting Focusing on the Sustainable Development Goals Using Remote Sensing and Geographical Information System

An innovative way to combat water scarcity brought on by population increase and climate change is rainwater harvesting (RWH), particularly in arid and semiarid areas. Currently, Pakistan is facing major water issues due to underprivileged water resource management, climate change, land use changes, and the sustainability of local water resources. This research aims to find out the suitable sites and options for RWH structures in the Quetta district of Pakistan by integrating the depression depth technique, Boolean analysis, and weighted linear combination (WLC) with hydrological modeling (HM), multicriteria analysis (MCA), a geographic information system (GIS), and remote sensing (RS). To find suitable sites for RWH, a collection of twelve (12) thematic layers were used, including the slope (SL), land use land cover (LULC), subarea (SA), runoff depth (RD), drainage density (DD), lineament density (LD), infiltration number (IFN), distance from built-up area (DB), distance from roads (DR), distance from lakes (DL), maximum flow distance (MFD), and topographic wetness index (TWI). The Boolean analysis and WLC approach were integrated in the GIS environment. The consistency ratio (CR) was calculated to make sure the assigned weights to thematic layers were consistent. Overall, results show that 6.36% (167.418 km2), 14.34% (377.284 km2), 16.36% (430.444 km2), 18.92% (497.663 km2), and 18.64% (490.224 km2) of the area are in the categories of very high, high, moderate, low, and very low suitability, respectively, for RWH. RWH potential is restricted to 25.35% (666.86 km2) of the area. This research also identifies the five (5) best locations for checking dams and the ten (10) best locations for percolation tanks on the streams. The conducted suitability analysis will assist stakeholders in selecting the optimal locations for RWH structures, facilitating the storage of water, and addressing the severe water scarcity prevalent in the area. This study proposes a novel approach to handle the problems of water shortage in conjunction with environmental and socioeconomic pressures in order to achieve the sustainable development goals (SDGs).

A Case Study on the Integration of Remote Sensing for Predicting Complicated Forest Fire Spread

Forest fires can occur suddenly and have significant environmental, economic, and social consequences. The timely and accurate evaluation and prediction of their progression, particularly the spread speed in difficult-to-access areas, are essential for emergency management departments to proactively implement prevention strategies and extinguish fires using scientific methods. This paper provides an analysis of models for predicting forest fire spread in China and globally. Incorporating remote sensing (RS) technology and forest fire science as the theoretical foundation, and utilizing the Wang Zhengfei forest fire spread model (1983), which is noted for its broad adaptability in China as the technical framework, this study constructs a forest fire spread model based on remote sensing interpretation. The model improves the existing model by adding elevation an factor and optimizes the method for acquiring certain parameters. By considering regional landforms (ridge lines, valley lines, and slopes) and vegetation coverage, this paper establishes three-dimensional visual interpretation markers for identifying hotspots; the orientation of the hotspots can be identified to simulate the spread of the fire uphill, downhill, in the direction of the wind, left-level slope, and right-level slope. Then, the data of Sentinel-2 and DEM were used to invert the fuel humidity and slope of pixels in the fire line areas. The statistical inversion data from pixels, which replaced fixed-point values in traditional models, were utilized for predicting forest fire spread speed. In this paper, the model was applied to the case of a forest fire in Mianning County, Sichuan Province, China, and verified using high-time-resolution Himawari-8 data, Gaofen-4 data, and historical data. The results demonstrate that the direction and maximum speed of fire spread for the fire lines in Baifen Mountai, Jiaguer Villageand, Muchanggou, Xujiabaozi, and Zhaizigou are uphill, 16.5 m/min; wind direction, 17.32 m/min; wind direction, 1.59 m/min; and wind direction, 5.67 m/min. The differences are mainly due to the locations of the fire lines, moisture content of combustibles, and maximum slopes being different. Across the entire fire line area, the average rate of increase in the area of open flames within one hour was 3.257 hm2/10 min (square hectares per 10 min), closely matching the average increase rate (3.297 hm2/10 min) monitored by the Himawari-8 satellite in 10 min intervals. In contrast, conventional fixed-point fire spread models predicted an average rate of increase of 3.5637 hm2/10 min, which shows a larger discrepancy compared to the Himawari-8 satellite monitoring results. Moreover, when compared to the fire spot monitoring results from the Gaofen-4 satellite taken 54 min after the initial location of the fire line, the predictions from the RS-enabled fire spread model, which integrates remote sensing interpretations, closely matched the actual observed fire boundaries. Although the predictions from the RS-enabled fire spread model and the traditional model both align with historical data in terms of the overall fire development trends, the RS-enabled model exhibits higher reliability and can provide more accurate information for forest fire emergency departments, enabling effective pre-emptive measures and scientific firefighting strategies.

GLE-net: global-local information enhancement for semantic segmentation of remote sensing images

Remote sensing (RS) images contain a wealth of information with expansive potential for applications in image segmentation. However, Convolutional Neural Networks (CNN) face challenges in fully harnessing the global contextual information. Leveraging the formidable capabilities of global information modeling with Swin-Transformer, a novel RS images segmentation model with CNN (GLE-Net) was introduced. This integration gives rise to a revamped encoder structure. The subbranch initiates the process by extracting features at varying scales within the RS images using the Multiscale Feature Fusion Module (MFM), acquiring rich semantic information, discerning localized finer features, and adeptly handling occlusions. Subsequently, Feature Compression Module (FCM) is introduced in main branch to downsize the feature map, effectively reducing information loss while preserving finer details, enhancing segmentation accuracy for smaller targets. Finally, we integrate local features and global features through Spatial Information Enhancement Module (SIEM) for comprehensive feature modeling, augmenting the segmentation capabilities of model. We performed experiments on public datasets provided by ISPRS, yielding notably remarkable experimental outcomes. This underscores the substantial potential of our model in the realm of RS image segmentation within the context of scientific research.

Characteristics and Correlation Study of Mountainous Lake Ice Phenology Changes in Xinjiang, China Based on Passive Microwave Remote Sensing Data

Lake ice phenology directly reflects local climate changes, serving as a key indicator of climate change. In today’s rapidly evolving climate, utilizing advanced remote sensing techniques to quickly extract long-term lake ice phenology features and studying their correlation with other climate factors is crucial. This study focuses on lakes in Xinjiang, China, with a mountainous area greater than 100 km2, including Sayram Lake, Ayahkum Lake, Achihkul Lake, Jingyu Lake, and Ahsaykan Lake. The Bayesian ensemble change detection algorithm was employed to extract lake ice phenology information, and the Mann–Kendall (MK) non-parametric test was used to analyze trends. The visual interpretation method was used to interpret the spatial evolution characteristics of lake ice, and the Pearson correlation coefficient was used to explore the driving factors of lake ice phenology. Results indicate the following: (1) Jingyu Lake exhibited the most significant delay in both freezing and complete freezing days, while Ayahkum Lake showed the most stable pattern. Ahsaykan Lake demonstrated the least delay in both starting and complete melting days. (2) Sayram Lake’s ice evolution was unstable, with wind causing variability in the locations where freezing begins and melting spreading from the west shore. Ayahkum Lake, Ahsaykan Lake, and Jingyu Lake exhibited similar seasonal variations, while Achihkul Lake’s ice spatial changes spread from the east to the center during freezing and from the center to the shore during melting. (3) The study found that the freeze–thaw process is influenced by a combination of factors including lake area, precipitation, wind speed, and temperature.