Remote Sensing Applications-Society and Environment最新文献

In today's era, increasing access to very high-resolution remote sensing images (VHR-RSIs) has enhanced building detection and change assessment capabilities. These applications provide accurate urban mapping, facilitate effective land management, and support disaster assessment by delivering detailed insights into building structures and their temporal changes. This study uses a two-stage process to present a pioneering approach for generating precise building maps (BMs) and subsequent building change maps (BCMs) from VHR-RSIs. The primary question addressed by the research is how to enhance the U-Net architecture to improve its sensitivity to both high-level semantic features (HLSF) and low-level spatial features (LLSF) in the building detection task. For this purpose, in the initial stage of the method, a novel deep learning model called dual attention residual-based U-Net (DAttResU-Net) is introduced. This model incorporates two significant modifications to the conventional U-Net, enhancing its capacity to yield bi-temporal BMs. Firstly, each standard convolutional block (CB) is replaced with an optimized CB incorporating a channel-spatial attention module attuned to the building objects' crucial HLSF. Secondly, an additional attention module is integrated into the encoder-decoder path of the model, heightening the sensitivity of U-Net to vital LLSF of buildings while disregarding extraneous background spatial information during the fusion of HLSF and LLSF. In the subsequent stage, the bi-temporal BMs generated by the DAttResU-Net are subjected to a box-based class-object change detection methodology to produce accurate BCMs. The effectiveness of the proposed architecture is rigorously evaluated against state-of-the-art models in both BM and BCM generation contexts, utilizing the well-established WHU dataset for experimentation. The experimental results indicated that the DAttResU-Net model, boasting an average of $P_{\text{FN}}$/ $P_{\text{FP}}$ value of 2.33/1.34 (%) surpasses the performance of the state-of-the-art models in generating bi-temporal BMs. Furthermore, the building change detection outcomes demonstrated the proficient role of the bi-temporal BMs predicted by the proposed model in leading to the most optimal BCMs, exhibiting average $P_{\text{FN}}$/ $P_{\text{FP}}$ value of 2.63/8.93 (%), outperforming comparative networks. Finally, we concluded that the proposed DAttResU-Net architecture is a highly promising and applicable model for producing reliable BMs and BCMs.

Accurate crop mapping using satellite imagery is crucial for improving the monitoring of agricultural landscapes. Very high resolution (VHR) satellite imagery offers unique capabilities in this respect, allowing for even small fields to be discerned and image texture analysis to be performed. Additionally, satellite imagery has greater efficiency than unmanned aerial vehicles due to its extensive coverage. Moreover, the operation flexibility of VHR satellites means that timely image acquisition is possible several times during the growing season. This study investigates the potential of VHR Pléiades images and the random forest classifier for accurate crop mapping. Four images acquired on April 9th, May 12th, May 31st, and June 20th were used to test 16 classification scenarios, including single-date and multi-temporal combinations of spectral bands, texture features, and vegetation Indices (VIs). The classification using the spectral bands from all four images achieved the highest overall accuracy, 93.9% and 96.3% at field and pixel levels, respectively. The bitemporal classifications had lower accuracy. Nevertheless, the combination of the May 12th and June 20th spectral bands had 90% accuracy, which indicated that two images may be sufficient for reliable mapping if the periods with phenological differences between crops are considered. Adding texture features to the spectral bands significantly enhanced the accuracy (up to 8%) of single-date classifications, making it highly recommended when only one image is available. However, the impact of texture was more pronounced on the later dates. It showed the most marked benefit for vineyards and alfalfa, with minimal or no improvement observed for other classes like winter barley. An additional increase in overall accuracy was achieved in three of the four dates by supplementing the spectral and texture bands with VIs. This study highlights the importance of considering image acquisition dates and crop types when designing satellite-based crop mapping strategies for optimal accuracy.

Implementing the Sentinel-1 SAR backscatter analysis ready data (S1ARD) preparation framework to Sentinel-1 C-band SAR data in the Google Earth Engine platform potentially enhances the quality of SAR data, facilitating the advancement of wide-scale, large-impact, and continuous SAR-supported RS applications such those for rice monitoring activities. Nevertheless, there is a lack of published works assessing different speckle filtering configurations available within the S1ARD preparation framework, particularly those directly associated with rice monitoring activities. This study quantitatively evaluated the performance of available speckle filtering parameters on the S1ARD preparation framework, analyzed their derived backscatter values over a rice-growing cycle, and utilized produced datasets as inputs to classify distinct classes of rice transplanting periods in two study areas by applying the random forest classifier. The backscatter analysis demonstrated that the mono-temporal speckle filtering frameworks yielded elevated backscatter values compared to the unfiltered dataset, which exhibited higher values than those derived by the multi-temporal frameworks. Furthermore, filtered datasets increased classification accuracies ranging from 9.30 - 13.95% and 17.23 - 25.94% in study area 1 and between 4.69 - 15.63% and 9.28 - 29.75% in study area 2, for OA and Kappa, respectively, than those produced by unfiltered datasets. Overall, the multi-temporal speckle filtering framework with a Lee filter, 15 number-of-image, and a 7 x 7 window configuration was recommended to apply to the S1ARD preparation framework to assist SAR-supported RS-based rice monitoring activities. Finally, the findings of this work offer direct guidance and recommendations about the behavior and contributions of Sentinel-1 C-band SAR data applied with distinct speckle filtering configurations yielded by benefiting the S1ARD preparation framework for aiding SAR-supported RS-based rice monitoring activities.

Forests provide multiple ecosystem services including water and soil protection, biodiversity conservation, carbon sequestration, and recreation, which are crucial in sustaining human health and wellbeing. Global changes represent a serious threat to Mediterranean forests, and among known impacts, there is the spread of invasive pests and pathogens, often boosted by climate change and human pressure. Remote sensing can provide support to forest health monitoring, which is crucial to contrast degradation and adopt mitigation strategies. Here, different multispectral and SAR data are used to detect the incidence of ink disease driven by Phytophthora cinnamomi in forest sites in central Italy, dominated by chestnut and cork oak respectively. Sentinel 1, Sentinel 2, and PlanetScope data, together with ground information, served as input in Random Forests to model healthy and disease classes in the two sites. The results indicate that healthy and symptomatic trees are clearly distinguished, whereas the discrimination among disease classes of different severity (moderate and severe damage) is less accurate. Crown dimension and sampled spectral regions are a critical factors in the selection of the sensor; better results are obtained for the larger chestnut crowns with Sentinel 2 data. In both sites, the red and near infra-red bands from multispectral data resulted well suited to monitor the spread of the ink disease.

Generating granular-scale surface albedo data is extremely important for solar photovoltaic site planning and to optimise renewable energy yield of bifacial panel installations. The albedo effect brings about a significant increase in power in bifacial photovoltaic systems, compared to their mono-facial counterparts, since the spectral response of bifacial solar panels correlates with the incident solar radiation wavelength on the back of the panel, to provide additional power generation capacity. Thus, harnessing the albedo data at relatively local scales is critical towards boosting solar power generation and providing greater power density in local electricity grids. This paper develops novel modelling approaches to produce high-resolution spectral albedo imagery across the Visible and Near Infrared (VNIR) bands, using the Wavelet-Fusion super-resolution model (i.e., Wavelet-FusionSR) trained with the Learned Gamma Correction approach by applying satellite image enhancement methodology. The proposed Wavelet-FusionSR model utilises the low-resolution moderate-resolution Imaging Spectroradiometer (MODIS) as well as high-resolution multi-spectral Advanced Space-borne Thermal Emission Reflection Radiometer (ASTER) satellite images, as critical inputs and ground-truth imagery, respectively, in order to perform sensor-to-sensor deep downscaling, without employing any synthetic or low-resolution satellite imagery data pairs. To augment the proposed deep learning algorithm across the decomposed sub-images of low-resolution inputs, we integrate local and global feature representation learning to train the proposed Wavelet-FusionSR model with Cauchy loss functions. In comparison with five competing benchmark models, the proposed Wavelet-FusionSR model demonstrates performance superiority using quantitative image downscaling metrics and visual assessments of the downscaled images for the visible band of solar radiation. The proposed Wavelet-FusionSR model yielded a Mean Square Error (MSE) of 0.00017, Signal-to-noise-ratio (PSNR) of 37.80, Structural Similarity Index (SSIM) of 0.999 and combined loss, MS-SSIMLoss, based on Multi Structural Similarity and Mean Absolute Error of 2.354 for the Visible Band images, and an MSE of 0.0014, PSNR of 28.43, SSIM of 0.999 and MS-SSIMLoss of 7.426 for the NIR spectral bands, demonstrating high efficacy of the proposed Wavelet-FusionSR method. The Wavelet-FusionSR method therefore attains high-resolution spectral albedo imagery outputs.

Forests are crucial in delivering ecosystem services that underpin human well-being and biodiversity conservation. However, these vital ecosystems are threatened by forest degradation and rapid urbanisation. This study addresses this challenge by proposing a comprehensive framework for mapping natural forests at the municipal scale. The framework integrates remote sensing techniques with machine learning algorithms to provide valuable insights into the extent of natural forests within the eThekwini Municipality. The study utilised Landsat 7, Landsat 8, and Landsat 9 satellite imagery to analyse and map the historical and current distribution of natural forests. Five spectral indices, namely, Normalized Differential Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), Chlorophyll Index Green (CIG), Enhanced Vegetation Index (EVI), and Enhanced Vegetation Index-2 (EVI-2), which were calculated from Landsat bands, were employed in the analysis. Light Gradient Boosting Machine (LightGBM), Categorical Boosting (CatBoost), and Extreme Gradient Boosting (XGBoost) machine learning algorithms were used to model forest distribution. Accuracy was assessed through confusion matrices, Receiver Operating Characteristic (ROC) Curves, area under the ROC curve (AUC), and the F1 scores. LightGBM achieved the highest overall accuracy (90.76%), followed by CatBoost (89.56%) and XGBoost (84.34%). LightGBM also obtained the best F1 score (90.76%). These findings highlight LightGBM's effectiveness in classifying natural forests, making it the preferred model for mapping the historical extent of natural forests in the eThekwini Municipality. However, classifications based on Landsat 7 significantly underestimated the extent of natural forests within the study area, whereas Landsat 8 and Landsat 9 data revealed an increase in natural forests from 2015 to 2023. These findings will guide effective and targeted forest rehabilitation and restoration efforts, ensuring the preservation and enhancement of forest ecosystem services.

This study explores the applicability of 13 globally-derived Chlorophyll-a (CHL) products from optical satellite remote sensing to support local water quality management in Lake Nicaragua. The temporal and spatial consistency between the products was analyzed, as well as their agreement with in-situ data collected from 2011 to 2016. The Climate Change Initiative (CCI) CHL product was identified as the most stable and reliable, suggesting its suitability for monitoring Lake Nicaragua. However, the correlation of this product with in-situ measurements was weak, attributed to the sparse and inconsistent nature of the available in-situ water quality data. The hotspots analysis identified critical areas around urban and agricultural zones with high CHL concentrations, providing valuable insights for targeted management interventions. This study emphasizes the need for improved global to local remote sensing strategies, including the selection of the appropriate algorithms for the region, continuous calibration and validation with in-situ data, and the development of a robust, publicly accessible local water quality database that includes both in-situ and remote sensing data, to support effective monitoring for local water management.

In agriculture, nitrogen (N) is a key element in plant nutrition that affects, both positively and negatively, the productive and qualitative results of the crop. Accurate quantification of nitrogen levels is crucial for devising effective plant nutrition strategies. The objective of this study was to validate a novel method to estimate the N content at different phenological stages of durum wheat (Triticum durum Desf. cv. Iride) under different N management strategies (chemical synthetic fertilizer - SYN and organic fertilizer - ORG) in Italy, using the Nitrogen Nutrition Index (NNI)as a diagnostic tool for improving nitrogen fertilization timing and doses. The NNI is the ratio between the actual crop nitrogen content (N_a) and the optimal level (N_c) required for ideal growth conditions.

On ground level, Leaf Area Index (LAI), Canopy reflectance, leaf chlorophyll content (LCC) and N concentration in leaves were measured. At landscape level, LAI and Canopy Chlorophyll Indices (CIs) were derived from Sentinel 2 (S2) multispectral images captured on the same days as the ground measurements: Chlorophyll Indexes were used for estimating the canopy chlorophyll content, CCC. N_a in leaves and canopy were calculated from LCC and CCC respectively.

In the study area, N_c is N_c = 4.65LAI^−0.35, R² = 0.92. Among the tested Chlorophyll Indices (CIs) regression models, the linear regression was the more accurate to predict Na content, even though most of the tested Chlorophyll Indices (CIs) showed an R² > 0.8,a. The best-performing spectral index in both calibration and validation steps resulted from the IRECI, with R² = 0.90 and RMSE = 0.31. The developed NNI well-captured the seasonal N dynamic for durum wheat, under different N management and meteorological conditions. The NNI calculated from S2 data for crop N status assessment, showed to be an accurate estimation of the Nitrogen Nutrition Index and can be used for the fertilization plans without costly on ground measurements.

A comprehensive understanding of the streamflow dynamic along the river system is one of the significant components for preserving biodiversity and ensuring sustainable ecological processes. Understanding this requirement, streamflow estimation using remote sensing (RS) has evolved as an alternate approach in the hydrologic literature during the last decade due to its extensive spatiotemporal coverage. However, the existing RS-based approaches have limited applications for deriving the continuous time series in tropical river reaches due to narrow water widths during the low flow and frequent cloud covers during the high flow periods. Therefore, this study proposed frameworks to establish a virtual monitoring station (VMS) where multi-mission satellites are being used to derive continuous streamflow time series. From the multi-mission satellites, the optical RS images are used to develop a Copula-based fusion (CFUS) model by integrating the Frank copula with the 30m × 1-day resolution synthetic Landsat images, derived from the fusion of 250m × 1-day resolution MODIS images and 30m × 16-days resolution Landsat images; whereas the water levels are retrieved from the altimeters to derive discharge using the rating curve. Additionally, the potential utility of the established VMS for hydrodynamic model (MIKE11-NAM-HD) calibration under data-scarce conditions is also demonstrated. Finally, a coupled RS-hydrodynamic (RS-HD) framework is also proposed to establish VMS both at semi-gauged and ungauged sections of the rivers. The efficacy of the aforementioned framework was tested along the lower Brahmani river reach. The results reveal that the advocated framework could perform satisfactorily with the Nash-Sutcliffe efficiency (NSE) and Kling-Gupta efficiency (KGE) ≥0.8. This approach has the potential to be upscaled to other river reaches as one of the next-generation hydrometry for daily streamflow monitoring using high-frequent observation of multi-mission satellites.

Cloud occlusion is a common problem in the field of remote sensing, particularly for retrieving Land Surface Temperature (LST). Remote sensing thermal instruments onboard operational satellites are supposed to enable frequent and high-resolution observations over land; unfortunately, clouds adversely affect thermal signals by blocking outgoing longwave radiation emission from the Earth’s surface, interfering with the retrieved ground emission temperature. Such cloud contamination severely reduces the set of serviceable LST images for downstream applications, making it impractical to perform intricate time-series analysis of LST. In this paper, we introduce a novel method to remove cloud occlusions from Landsat 8 LST images. We call our method ISLAND, an acronym for Interpolating Land Surface Temperature using land cover. Our approach uses LST images from Landsat 8 (at 30 m resolution with 16-day revisit cycles) and the NLCD land cover dataset. Inspired by Tobler’s first law of Geography, ISLAND predicts occluded LST through a set of spatio-temporal filters that perform distance-weighted spatio-temporal interpolation. A critical feature of ISLAND is that the filters are land cover-class aware, making it particularly advantageous in complex urban settings with heterogeneous land cover types and distributions. Through qualitative and quantitative analysis, we show that ISLAND achieves robust reconstruction performance across a variety of cloud occlusion and surface land cover conditions, and with a high spatio-temporal resolution. We provide a public dataset of 20 U.S. cities with pre-computed ISLAND LST outputs. Using several case studies, we demonstrate that ISLAND opens the door to a multitude of high-impact urban and environmental applications across the continental United States.