Remote Sensing Applications-Society and Environment最新文献

Small pelagic fish are an essential resource for coastal countries worldwide and their assessment and monitoring are a key part of successful fisheries management. Advances in marine satellite remote sensing can contribute to the creation of methodologies for continual small pelagic fish spatial distribution monitoring that can act as supplementary tools for fisheries management decision making, enhancing traditional field practices. In this work a comprehensive Geospatial Web Service (GWS) is proposed that utilizes Sentinel-3 data to publish Spatial Distribution Modeling (SDM) maps for anchovy (Engraulis encrasiculous) and sardine (Sardina pilchardus). The proposed GWS is developed through the sole use of open-source programming languages and software and provides fishery management related data through various parameters: A) Sea Surface Temperature (SST) and Chlorophyll-a Concentration (CHL), B) mesoscale oceanic fronts and C) the SDM maps for the target species. The SDM results are produced through a Random Forest algorithm and utilized oceanographic parameters relevant to the ecological needs of the target species (CHL, SST, oceanic fronts and bathymetry). All data are processed and gap-free through a spatiotemporal DINEOF interpolation, allowing the continuous provision of information independently of the weather conditions. Furthermore, the service integrates auxiliary information, such as weather and sea state forecasts, that aim to contribute to maritime safety for effective decision-making. The resulting GWS offers an easy to use and interactive tool that bridges the gap between the scientific community and the decision makers. The utilization of satellite remote sensing enhances the scalability of the proposed service for future improvements and continuous monitoring.

The study addresses the challenge of sustainable land management, which is crucial for agricultural production and soil quality (SQ), in the face of land degradation that negatively impacts crop production and SQ. The goal of the current work is to assess SQ using digital soil mapping (DSM) in Kafr El-Sheikh province, Egypt, to develop a framework employing two methods for soil quality index (SQI) assessment: the total data set (SQI-TDS) and a selected minimum data set (SQI-MDS) to choose indicators, along with a weighted additive SQI (SQI_w), and a Random Forest (RF) model to predict and map the SQI, as well as the salt-affected soil indicators (EC, pH, and ESP). This framework uses remote sensing data: time series of Sentinel-1 (S-1) and Sentinel-2 (S-2) greenest pixel composite. Additionally, we incorporated environmental covariates derived from S-1 and S-2 imagery to understand their influence on SQ, which in turn informs land management practices, land degradation assessment, and crop productivity. The findings reveal a clear negative impact of salinity and alkalinity on SQ. We demonstrate the importance of Variance Inflation Factor (VIF) and Sequential Feature Selection (SFS) techniques for improving the performance of the RF model used for prediction. Notably, the greenest pixel composite imagery proved promising for SQI assessment using DSM beneath vegetation cover, crop mapping, and land-use dynamics. The precise SQI obtained is essential for decision-makers to detect land degradation, develop sustainable agricultural management strategies, and assess their appropriateness for developing plans and strategies to increase agricultural productivity.

Accurate land-cover mapping in regions with frequent cloud-cover and rapidly changing agricultural land cover by crop growth cycles cannot be guaranteed by use of single sensor images, or an image from a single-acquisition-date. This study addressed these challenges by applying temporal-aggregation of single sensor image features that is integrated with multi-sensor image fusion. Results of land-cover classification target fallow, growing, and harvest/post-harvest agricultural seasons. Satellite based features used were frequency bands of Sentinel-1 (S1) and Sentinel-2 (S2), including vegetation indices (VIs) and biophysical variables (BPVs). Temporal aggregation improved classification accuracy. The single-acquisition-date S2 image, overall accuracy (OA) ranged from 0.81 to 0.85, increased to 0.86 to 0.87 after temporal-aggregation. Meanwhile, for single-acquisitions of S1, OA ranged from 0.44 to 0.79 increased to 0.6 to 0.86 across respective seasons. Fusing temporally aggregated S1 and S2 image features including VIs and BPVs increased OA up to 0.90. Selecting 11, 8, and 10 out of 18 optimum numbers of features for fallow, growing, and harvest/post-harvest seasons respectively improved OA by 3%, 2%, and 1.86%. PCA fusion of the temporally aggregated best performing feature set enhanced harvest/post-harvest season, fallow, and growing seasons with OA of 0.98, 0.96 and 0.94 respectively. Accuracy was enhanced when selecting different best performing feature set for the three seasons. The study enhanced knowledge of advanced remote sensing for agricultural land cover mapping, with practical implications of land monitoring and management.

Satellite images are essential tools for monitoring aquatic ecosystems and assessing water quality, as they enable the measurement of parameters such as chlorophyll-a (Chl-a) concentration, phycocyanin (PC), and cyanobacteria density. These indicators aid in evaluating eutrophication processes and detecting cyanobacteria in aquatic ecosystems. This study utilized field data and images captured by the Sentinel-2 sensor from 2015 to 2022 to investigate the Jaguari-Jacareí reservoirs (JAG-JAC). Two atmospheric corrections from the Case 2 Regional Coast Color (C2RCC) processor, namely C2X and C2XC, were applied, and algorithms were developed to estimate the parameters using both in situ data measurements and reflectance data extracted from the images. For Chl-a concentration, the dataset was divided into two blocks: one for model calibration (70% of the data) and the other for validation (30% of the data). As for PC, the entire dataset was utilized to calibrate the model, and validation was conducted through cross-validation using the Automated Radiative Transfer Model Operator (ARTMO) software. Cyanobacteria density was indirectly estimated from the Chl-a concentrations determined in the field samples, as these variables exhibited a strong correlation, also validating the model previously proposed for the Cantareira system for estimating cyanobacteria density from Chl-a data. Additionally, the automatic chlorophyll-a products (con_chla) derived from the C2X and C2XC processors were validated. The findings revealed that the C2X processor exhibited the greatest potential for estimating water quality parameters. It was observed that the most effective algorithms were derived using the R705/R665 band ratio for Chl-a and the R705/R490 ratio for PC. For cyanobacteria density, the optimal algorithm was established based on the relationship between cyanobacteria density and Chl-a using the data obtained in this study.

The analysis of land-use and land-cover (LULC) changes is crucial for rural development planning, food security monitoring, and natural resource conservation. This study focuses on detecting LULC changes in Amibara and Awash-Fentale districts from 1985 to 2021. We utilized five sets of Landsat data (Landsat 5 TM for 1985, 1995, 2002, and Landsat 8 OLI for 2015 & 2020) and applied supervised maximum likelihood classification. Accuracy assessments revealed overall accuracies ranging from 88.9% to 95.3% for Amibara and 89.5%–93.2% for Awash-Fentale. Both districts exhibited six main LULC classes: agriculture, bareland, built-up, mixed forest, shrubland, and water bodies. In Amibara LULC changes from 1985 to 2021 revealed significant shifts, maintaining its primary bareland characteristic, concentrated agriculture, and expanding Prosopis-dominated shrubland due to livestock-mediated seed dispersal. Conversely, in Awash-Fentale bareland dominance decreased from 92.28% to 67.02%, while agriculture, built-up areas, and shrubland expanded. Water bodies emerged between 2015 and 2021 which is associated with the construction of Kesem Kebena dam for sugar cane farm production. The net gains were observed in shrubland (12.9%), agriculture (5.8%), mixed forest (4.1%), water bodies (1.5%), and built-up areas (0.9%), with bareland experiencing a loss of 25.3%. In conclusion, Amibara and Awash-Fentale underwent both comparable and distinct LULC shifts, featuring prevalent bareland and central agriculture, alongside Prosopis-driven shrubland expansion due to livestock dispersal. While mixed forest exhibited fluctuations, built-up areas and water bodies remained limited. Notably, Awash-Fentale showed higher LULC variability. Understanding these land cover changes helps assess vulnerability to climate impacts like droughts and floods, enhancing climate resilience. Insights from this study can inform sustainable land-use planning, conservation strategies, and policy interventions in the Afar region and similar areas. These observations highlight the need for integrated land management approaches that balance socioeconomic development with environmental sustainability.

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.

Land use and land cover (LULC) analysis provides valuable information to understand environmental changes and their effects on landslide occurrence. However, LULC time series can be affected by errors in classifications that lead to invalid transitions and, therefore, to misinterpretations. One solution is to include temporal approaches that reduce the effects of invalid transitions. Here, we aimed to evaluate how such methods can improve the LULC analysis for a landslide-affected area. For that, we integrated the Random Forest (RF) class likelihoods with the temporal approach provided by the Compound Maximum a Posteriori (CMAP) algorithm, named here as RF-CMAP. Results from RF-CMAP were compared to those obtained from the traditional RF in a post-classification comparison approach. Although both methods presented high performance, with overall accuracy (OA) values greater than 0.87, RF-CMAP reached higher OA than RF for all the analysed years and corrected 99.92 km² (12% of the total area) of invalid transitions presented by the traditional RF. Furthermore, RF-CMAP was capable of correctly classifying more areas than RF in landslides (e.g., 66% and 21% for RF-CMAP and RF in 2000, respectively). Finally, this study contributes to exploring the integration between RF and CMAP algorithms to avoid invalid transitions and to assess how the existence of LULC invalid transitions can impact subsequent analyses.

There is ample evidence that environmental justice communities experience high levels of extreme heat. However, it is unknown how disparities in urban heat exposure and adaptation options change over time. This study investigates socioeconomic disparities over time in urban heat exposure and adaptation options in eight mid-sized Northeastern cities. We ask: How were socioeconomic factors associated with heat exposure and adaptation options over time? We analyzed disparities at the census block group level and census block level, respectively. At the census block group level, we ran spatial regression models between socioeconomic variables, including race, income, gender, and age, and heat exposure and adaptation variables, including land surface temperature, normalized different vegetation index (NDVI), tree cover, and air conditioning ownership rate. We found that: Low median household income is always associated with high LST and low NDVI from 1990 to 2020; Low percentages of females are always associated with high LST and low NDVI from 1990 to 2020. High percentages of POC are associated with high LST in 2010 and 2020, but not in 1990 and 2000; Low median household income and low percentages of elderly are associated with lower tree covers; High percentages of POC, low percentages of elderly, and low median household income are associated with lower AC rates. In analysis at the census block level by city, we found that disparities in urban heat exposure between predominantly POC and predominantly white communities increased in most cities during 1990–2020. Predominantly POC communities consistently have lower vegetation cover over time in most cities. Disparities in vegetation cover per unit area increased in most cities, whereas disparities in vegetation cover per capita decreased in most cities. Our findings of the trends in disparities in heat exposure and adaptation are useful for forecasting disparities in the future. These findings also suggest that interventions should prioritize cities with increasing disparities in heat exposure and adaptation.

There is a growing amount of literature that focuses on using machine learning algorithms to predict poverty from satellite and aerial images on a low regional level, particularly for countries without a high-quality official statistical system. The data used for annotating images and training an algorithm are generally based on sample surveys. In The Netherlands, statistics on income and poverty are derived from tax registers resulting in a complete enumeration of the Dutch population. In this paper, we use this complete enumeration to simulate to which extent satellite or aerial images can predict poverty on low regional levels. After geocoding these households, aerial images are annotated and a deep learning algorithm is trained to predict poverty. The precision of the predictions is evaluated by comparing it with the true poverty fractions known from tax registers. The effect of different spatial scales (1-ha vs. 25-ha images), spectral bands (RGB vs. CIR), and sample sizes for the training set are compared. It is discussed how this information can be used in the production of low regional statistics on poverty in countries where high-quality official statistical systems are lacking.