摘要：
The estimation of forest above-ground biomass (AGB) can be significantly improved by leveraging remote sensing (RS) and deep learning (DL) techniques. In this process, it is crucial to obtain appropriate RS features and develop a suitable model. However, traditional methods such as random forest (RF) feature selection often fail to adequately consider the complex relationships within high-dimensional RS feature spaces. Moreover, challenges related to parameter selection and overfitting inherent in DL models may compromise the accuracy of AGB estimation. Therefore, this study proposes a novel framework based on freely available Sentinel-1 synthetic aperture radar (SAR) and Sentinel-2 optical data. Firstly, we designed new indices through the formula analogous with vegetation index calculation to integrate multidimensional spectral and structural information. Then, leveraging the simplicity of computational principles, a pigeon-inspired optimization algorithm (PIO) was introduced into a bi-directional long short-term memory neural network (PIO-BiLSTM), which achieved the set objective function through repeated iteration and validation to obtain the optimal model parameters. Finally, to verify the framework's effect, we conducted experiments in two different tree species and compared another seven classical optimization algorithms and machine learning models. The results indicated that the new indices significantly improved the inversion accuracy of all models in both categories, and the PIO-BiLSTM model achieved the highest accuracy (Category-1: R2 = 0.8055, MAE = 8.8475 Mg center dot ha-1, RMSE = 12.2876 Mg center dot ha-1, relative RMSE = 18.1715%; Category-2: R2 = 0.7956, MAE = 1.7103 Mg center dot ha-1, RMSE = 2.2887 Mg center dot ha-1, relative RMSE = 9.3000%). Compared with existing methods, the proposed framework greatly reduced the labor costs in parameter selection, and its potential uncertainty also decreased by up to 9.0%. Furthermore, the proposed method has a strong generalization ability and is independent of tree species, indicating its great potential for future forest AGB inversion in wider regions with diverse forest types.
关键词：
LUCC;water quality;coupling;satellite remote sensing;Dongjiang Lake watershed
摘要：
With rapid social and economic development, land use/land cover change (LUCC) has intensified with serious impacts on water quality in the watershed. In this study, we took Dongjiang Lake watershed as the study area and obtained measured data on water quality parameters from the watershed's water quality monitoring stations. Based on Landsat-5, Landsat-8, or Sentinel-2 remote sensing data for multiple periods per year between 1992 and 2022, the sensitive satellite bands or band combinations of each water quality parameter were determined. The Random Forest method was used to classify the land use types in the watershed into six categories, and the area proportion of each type was calculated. We established machine learning regression models and polynomial regression models with WQI as the dependent variable and the area proportion of each land use type as the independent variable. Accuracy test results showed that, among them, the quadratic cubic polynomial regression model with grassland, forest land, construction land, and unused land as its independent variables was the best model for coupling watershed water quality with LUCC. This study's results provide a scientific basis for monitoring spatial and temporal changes in water quality caused by LUCC in the Dongjiang Lake watershed.
关键词：
CA-Markov;Dongjiang Lake Watershed;LUCC;Quantitative prediction
摘要：
Land Use/ Cover Change (LUCC) plays a crucial role in influencing hydrological processes, nutrient cycling, and sediment transport in watersheds, ultimately impacting water quality on both spatial and temporal scales. Accurately predicting changes in watershed water quality is beneficial for the sustainable management of water resources. Current models often lack the ability to effectively predict water quality changes in a dynamic spatio-temporal context, particularly in complex watershed environments. The overall purpose of the study is to establish a comprehensive and dynamic modeling framework that links LUCC with water quality, allowing for accurate predictions of future water quality under varying land use scenarios. The model, which uses water quality as the dependent variable and LUCC as the independent variable, was developed to quantitatively predict changes in watershed water quality. To achieve this, annual multi-period remote sensing images from Landsat-5, Landsat-8 or Sentinel-2 satellites spanning from 1992 to 2022 were analyzed. Random Forest (achieving a Kappa coefficient of 0.9468) were employed to classify land use within the watershed. Based on classification results, a Cellular Automata-Markov chain model (CA-Markov) was constructed to simulate and predict the spatio-temporal patterns of land use, incorporating driving factors such as proximity to water systems, roads, elevation, and slope. Validation of the model using LUCC data from 2020 yielded a high prediction accuracy with a Kappa coefficient of 0.9505. The CA-Markov model was further utilized to project LUCC under three different scenarios-natural development, ecological protection, and arable land protection-between 2023 and 2033. Based on these projections, the coupled water quality and LUCC model was employed to predict water quality changes in the watershed over the same period. Key findings indicate that water quality is likely to improve under ecological protection scenario, while deterioration is expected under natural development scenario and cropland protection scenario due to urban expansion, agricultural practices, and water diversion for irrigation. This study provides a robust framework for watershed management, offering scientific guidance for source management and water purification efforts, thereby contributing significantly to the sustainable development of water resources.
通讯机构：
[Gui Zhang] C;College of Forestry, Central South University of Forestry and Technology, Changsha 410004, China<&wdkj&>Author to whom correspondence should be addressed.
关键词：
remote sensing;burned area;subpixel mapping;GaoFen (GF) series data sets;forest fire
摘要：
<jats:p>The accurate detection of burned forest area is essential for post-fire management and assessment, and for quantifying carbon budgets. Therefore, it is imperative to map burned areas accurately. Currently, there are few burned-area products around the world. Researchers have mapped burned areas directly at the pixel level that is usually a mixture of burned area and other land cover types. In order to improve the burned area mapping at subpixel level, we proposed a Burned Area Subpixel Mapping (BASM) workflow to map burned areas at the subpixel level. We then applied the workflow to Sentinel 2 data sets to obtain burned area mapping at subpixel level. In this study, the information of true fire scar was provided by the Department of Emergency Management of Hunan Province, China. To validate the accuracy of the BASM workflow for detecting burned areas at the subpixel level, we applied the workflow to the Sentinel 2 image data and then compared the detected burned area at subpixel level with in situ measurements at fifteen fire-scar reference sites located in Hunan Province, China. Results show the proposed method generated successfully burned area at the subpixel level. The methods, especially the BASM-Feature Extraction Rule Based (BASM-FERB) method, could minimize misclassification and effects due to noise more effectively compared with the BASM-Random Forest (BASM-RF), BASM-Backpropagation Neural Net (BASM-BPNN), BASM-Support Vector Machine (BASM-SVM), and BASM-notra methods. We conducted a comparison study among BASM-FERB, BASM-RF, BASM-BPNN, BASM-SVM, and BASM-notra using five accuracy evaluation indices, i.e., overall accuracy (OA), user’s accuracy (UA), producer’s accuracy (PA), intersection over union (IoU), and Kappa coefficient (Kappa). The detection accuracy of burned area at the subpixel level by BASM-FERB’s OA, UA, IoU, and Kappa is 98.11%, 81.72%, 74.32%, and 83.98%, respectively, better than BASM-RF’s, BASM-BPNN’s, BASM-SVM’s, and BASM-notra’s, even though BASM-RF’s and BASM-notra’s average PA is higher than BASM-FERB’s, with 89.97%, 91.36%, and 89.52%, respectively. We conclude that the newly proposed BASM workflow can map burned areas at the subpixel level, providing greater accuracy in regards to the burned area for post-forest fire management and assessment.</jats:p>
摘要：
Forest fires can destroy millions of acres of land at shockingly fast speeds. The forest fire points identification algorithm is the most critical step in the forest fire monitoring process. Most traditional forest fire monitoring methods use fixed thresholds, ignoring background pixels, and have low recognition rates, which could lead to many problems, such as false reporting and low recognition rate. This paper proposes and tests an adaptive forest fire points identification algorithm using Himawari-8 data. By calculating the three-dimensional histogram of brightness temperature, an adaptive threshold that can automatically identify potential forest fire points is obtained. Based on this three-dimensional Otsu method, the contextual test algorithm has also been adopted to specify forest fire points. The experimental results show that the omission rate of the improved algorithm is about 10% lower than that of the previous algorithm in small-scale fire incidents. The improved algorithm can quickly and effectively extract fire point information, and it is also sensitive to small and low-temperature fires, which provides an efficient means for monitoring fire disasters.
作者机构：
[熊迎军] College of Information Science and Technology, Nanjing Agricultural University, Nanjing, 210095, China;[周俊; 韦玮; 沈明霞; 张保华] College of Engineering, Nanjing Agricultural University, Nanjing, 210031, China
通讯机构：
College of Engineering, Nanjing Agricultural University, Nanjing, China
关键词：
Land cover change;Dongting Lake;support vector machine;Landsat TM/OLI
摘要：
Land cover in Dongting Lake region has been faced high variations during recent decades. Therefore , there has a strong need to investigate and understand the land cover changes in Dongting Lake region between land cover types. In this study, support vector machine (SVM) classification method was employed to detect changes in land cover dynamic in Dongting Lake region using Landsat images for the year 1995, 2006 and 2015. Land cover information was classified to five categories: waterbody, wetland, built-up, cropland and forestland. Quantitative analysis , change detection matrix and land cover dynamic degree were utilized for investigating and assessing the land cover changes in Dongting Lake region. The overall accuracy (OA) and kappa coefficient of the land cover classification results were over 96% and 0.9, respectively. The results indicated that in 1995 about 11.32% of study area was covered by water-body together with 13.31% of wetland. Nearly 50% of the area was covered by cropland and remaining 2.59% was covered by built-up. During the period 1995-2015, the change rate of the waterbody was evaluated at-0.29%, at-0.67% for the wetland and at-2.47% for the built-up. On the contrary, the for-estland and cropland increased by 0.72% and 0.03%, respectively. In addition, the results of this study can provide scientific information for government to formulate policy for sustainable land use management in Dongting Lake region. Land cover change, Dongting Lake, support vector machine , Landsat TM/OLI Land cover changes affect global climate, species diversity and ecosystem balance, which can accelerate land degradation and reduce ecosystem services [1, 2]. It has become a serious environmental problem. Over the past few decades, land cover in Dongting Lake region experienced tremendous changes by natural processes, as well as anthropo-genic activities [3]. In particular, anthropogenic activities , such as reclaiming cropland from lakes and returning cropland to lakes, have become a major concern of land cover changes in Dongting Lake region [4]. Therefore, a clear understanding of the spatial and temporal changes of land cover types in the Dongting Lake region in recent two decades is important. Remote sensing has been monitoring and capturing the earth land's surface every day and night by providing spatial and temporal images over large and inaccessible area for more than six decades [5]. Therefore, remote sensing became an acknowledged technology for monitoring the land cover changes. Some optical remote sensing products, such as Moderate Images Spectrometer (MODIS), Advanced Very High-Resolution Radiometer (AVHRR), and Satellite Pour 1'Obervation de la Terre (SPOT) with resolution at 250 m to 1 km, are the very suitable data resources for studying information of earth surface [1, 6-11]. Despite short revisiting cycle and large swath width, these low-resolution products are mainly available on the detecting of large scale coarse land cover changes, but the transformation details of land cover types and its ratio remains unknown which usually occurs at a small scale. In order to settle these problems and detail monitoring earth's land cover changes, medium remote sensing satellite data, such as Landsat Thematic Mapper (TM) [12, 13], Landsat Enhanced Thematic Mapper Plus (ETM+) [7, 14] and Landsat Operational Land Im-ager (OLI) [12, 15], with resolution of 30 m but re-visiting cycle of 16 day, have been widely utilized for mapping land cover and monitoring its changes. Numerous researches have been conducted and various algorithms have been developed for detecting land cover changes especially over Dongting Lake region using remote sensing satellite technologies. Li et al. [16] employed the Geographical Information System (GIS) and Remote Sensing (RS) technologies to study the characterized long-term land cover changes in Dongting Lake region using the Landsat images from 1978, 1989, 1998. Their results indicated that land cover patterns in Dongting Lake region had been greatly altered by empoldering. Three land type had changed remarkably. The cultivated land decreased,
