Search

Soil salinization has become one of the major environmental problems threatening food security. The identification and knowledge of the spatial distributions of soil salinization are key in addressing this problem. This study assumes that a good saline land identification effect can be obtained with the help of deep learning methods. Therefore, this study used the OLI sensor data from the Landsat-8, based on the U2-Network, and proposes a method to extract saline land from remote sensing images. The study also adds different salinity indices (SI, SI1, and SI2) to explore its impact on classification accuracy. Through our method, accurate saline soil distribution information were obtained, and several verification indicators (the Intersection-over-Union (IoU), recall, precision, and F1-score) were all measured above 0.8. In addition, compared with the multi-spectral training results, the classification accuracy increased after adding a specific salinity index, and most of the accuracy indices increased by about 2% (the IoU increased by 3.70%, recall increased by 1.50%, precision increased by 2.81%, and F1-score increased by 2.13%). In addition, we also included a case study based on our methodology to analyze the distribution characteristics and changes of saline soil in the Zhenlai area of Northeast China from 2016 to 2020. We found that the area of saline land in the Zhenlai area has reduced, which shows that the extraction method proposed in this study is feasible. Overall, this paper indicates that deep learning-based methods can efficiently extract the salinity of soil and enhance the mapping of its spatial distribution. The study has the broad impact of supplementing satellite imagery for salinity modeling and helping to guide agricultural land management practices for northeastern China and other salinized regions. [ABSTRACT FROM AUTHOR]

Extraterrestrial solar radiation (ESR) is the essential basic background for solar radiation, which determines the occurrence of the weather and atmospheric phenomena. Since the influence of ESR variation on actual rugged terrain is a diverse, complex, and dynamic process, simulating ESR over a large spatial-temporal span, especially with a high-resolution digital elevation model (DEM), is a significant challenge. In this paper, we developed a new scheme for simulating ESR over the entirety of China using a DEM with a resolution of 30 m. To fully consider regional terrain status, the feature variables used were elevation, slope, and aspects of the located grid and the surrounding four grids to reveal the topography. In addition, latitude was used as a feature variable to consider the geographical location, and the month number was used to consider the duration. On the basis of different geographical locations, the training dataset was established from 20,000 grids. With the feature variable composition and training dataset, a backpropagation artificial neural network (BP ANN) was found to have the best performance compared with the other three machine learning methods in simulating ESR for a DEM. In terms of the proposed scheme and BP ANN, we drew an ESR map of China with a resolution of 30 m. The determination coefficient of the simulation result achieved 0.99 and the root-mean-square error was less than 50 MJ/m2 in all sample areas, confirming its remarkable accuracy. In terms of efficiency, the time consumption of ESR simulated using the proposed scheme shrinks over 150 times in all sample areas compared to that simulated via the theoretical model. Simultaneously, the developed scheme was also used to simulate an ESR for a DEM with a resolution of 90 m to verify the universality and robustness of the developed scheme. In addition, we used the proposed scheme to derive the direct solar radiation and global solar radiation, thereby further proving the reliability and applicability of our study. Overall, our work convincingly proved that the proposed scheme is a potential and effective approach for quickly simulating ESR with high accuracy. This study provides the basis for different solar radiation inversions of long time series and large spatial scales, offering additional insights for simulating ESR on a large spatial-temporal span. [ABSTRACT FROM AUTHOR]

As one of the most devastating disasters to pine forests, pine wilt disease (PWD) has caused tremendous ecological and economic losses in China. An effective way to prevent large-scale PWD outbreaks is to detect and remove the damaged pine trees at the early stage of PWD infection. However, early infected pine trees do not show obvious changes in morphology or color in the visible wavelength range, making early detection of PWD tricky. Unmanned aerial vehicle (UAV)-based hyperspectral imagery (HI) has great potential for early detection of PWD. However, the commonly used methods, such as the two-dimensional convolutional neural network (2D-CNN), fail to simultaneously extract and fully utilize the spatial and spectral information, whereas the three-dimensional convolutional neural network (3D-CNN) is able to collect this information from raw hyperspectral data. In this paper, we applied the residual block to 3D-CNN and constructed a 3D-Res CNN model, the performance of which was then compared with that of 3D-CNN, 2D-CNN, and 2D-Res CNN in identifying PWD-infected pine trees from the hyperspectral images. The 3D-Res CNN model outperformed the other models, achieving an overall accuracy (OA) of 88.11% and an accuracy of 72.86% for detecting early infected pine trees (EIPs). Using only 20% of the training samples, the OA and EIP accuracy of 3D-Res CNN can still achieve 81.06% and 51.97%, which is superior to the state-of-the-art method in the early detection of PWD based on hyperspectral images. Collectively, 3D-Res CNN was more accurate and effective in early detection of PWD. In conclusion, 3D-Res CNN is proposed for early detection of PWD in this paper, making the prediction and control of PWD more accurate and effective. This model can also be applied to detect pine trees damaged by other diseases or insect pests in the forest. [ABSTRACT FROM AUTHOR]

Cloud recognition is a basic task in ground meteorological observation. It is of great significance to accurately identify cloud types from long-time-series satellite cloud images for improving the reliability and accuracy of weather forecasting. However, different from ground-based cloud images with a small observation range and easy operation, satellite cloud images have a wider cloud coverage area and contain more surface features. Hence, it is difficult to effectively extract the structural shape, area size, contour shape, hue, shadow and texture of clouds through traditional deep learning methods. In order to analyze the regional cloud type characteristics effectively, we construct a China region meteorological satellite cloud image dataset named CRMSCD, which consists of nine cloud types and the clear sky (cloudless). In this paper, we propose a novel neural network model, UATNet, which can realize the pixel-level classification of meteorological satellite cloud images. Our model efficiently integrates the spatial and multi-channel information of clouds. Specifically, several transformer blocks with modified self-attention computation (swin transformer blocks) and patch merging operations are used to build a hierarchical transformer, and spatial displacement is introduced to construct long-distance cross-window connections. In addition, we introduce a Channel Cross fusion with Transformer (CCT) to guide the multi-scale channel fusion, and design an Attention-based Squeeze and Excitation (ASE) to effectively connect the fused multi-scale channel information to the decoder features. The experimental results demonstrate that the proposed model achieved 82.33% PA, 67.79% MPA, 54.51% MIoU and 70.96% FWIoU on CRMSCD. Compared with the existing models, our method produces more precise segmentation performance, which demonstrates its superiority on meteorological satellite cloud recognition tasks. [ABSTRACT FROM AUTHOR]

It is an objective demand for sustainable agricultural development to realize fast and accurate cultivated land quality assessment. In this paper, Tengzhou city (county-scale hilly area: scale A), Shanghe county (county-scale plain area: scale B), and Huang-Huai-Hai region (including large-scale hilly and plain area: scale C and D) were taken as research areas. Through the conversion of evaluation systems, the inversion models at the county-scale were constructed. Then, the image scale conversion was carried out based on the numerical regression method, and the upscaling inversion was realized. The results showed that: (1) the conversion models of evaluation systems (CMES) are Y = 1.021x − 4.989 (CMESA−B), Y = 0.801x + 16.925 (CMESA−C), and Y = 0.959x + 3.458 (CMESC−D); (2) the booting stage is the best inversion phase; (3) the back propagation neural network model based on the combination index group (CI-BPNN) is the best inversion model, with the R2 are 0.723 (modeling set) and 0.722 (verification set). CI-BPNN and CI-BPNN-CMESA−B models are suitable for the hilly and plain areas at the county-scale, and the level area ratio difference is less than 4.87%. Furthermore, (4) the reflectance conversion model of short-wave infrared 2 is cubic, and the rest are quadratic. CI-BPNN-CMESA−C and CI-BPNN-CMESA−C-CMESC−D models realized upscaling inversion in the hilly and plain areas, with the maximum level area ratio difference being 1.60%. Additionally, (5) the wheat field quality has improved steadily since 2001 in the Huang-Huai-Hai region. This study proposes an upscaling inversion method of wheat field quality, which provides a scientific basis for cultivated land management and agricultural production in large areas. [ABSTRACT FROM AUTHOR]

Landslides pose a constant threat to the lives and property of mountain people and may also cause geomorphological destruction such as soil and water loss, vegetation destruction, and land cover change. Landslide susceptibility assessment (LSA) is a key component of landslide risk evaluation. There are many related studies, but few analyses and comparisons of models for optimization. This paper aims to introduce the Tree-structured Parzen Estimator (TPE) algorithm for hyperparameter optimization of three typical neural network models for LSA in Shuicheng County, China, as an example, and to compare the differences of predictive ability among the models in order to achieve higher application performance. First, 17 influencing factors of landslide multiple data sources were selected for spatial prediction, hybrid ensemble oversampling and undersampling techniques were used to address the imbalanced sample and small sample size problem, and the samples were randomly divided into a training set and validation set. Second, deep neural network (DNN), recurrent neural network (RNN), and convolutional neural network (CNN) models were adopted to predict the regional landslides susceptibility, and the TPE algorithm was used to optimize the hyperparameters respectively to improve the assessment capacity. Finally, to compare the differences and optimization effects of these models, several objective measures were applied for validation. The results show that the high-susceptibility regions mostly distributed in bands along fault zones, where the lithology is mostly claystone, sandstone, and basalt. The DNN, RNN, and CNN models all perform well in LSA, especially the RNN model. The TPE optimization significantly improves the accuracy of the DNN and CNN (3.92% and 1.52%, respectively), but does not improve the performance of the RNN. In summary, our proposed RNN model and TPE-optimized DNN and CNN model have robust predictive capability for landslide susceptibility in the study area and can also be applied to other areas containing similar geological conditions. [ABSTRACT FROM AUTHOR]

In this paper, a deep learning long-short-term memory (LSTM) method is applied to the forecasting of the critical frequency of the ionosphere F2 layer (foF2). Hourly values of foF2 from 10 ionospheric stations in China and Australia (based on availability) from 2006 to 2019 are used for training and verifying. While 2015 and 2019 are exclusive for verifying the forecasting accuracy. The inputs of the LSTM model are sequential data for the previous values, which include local time (LT), day number, solar zenith angle, the sunspot number (SSN), the daily F10.7 solar flux, geomagnetic the Ap and Kp indices, geographic coordinates, neutral winds, and the observed value of foF2 at the previous moment. To evaluate the forecasting ability of the deep learning LSTM model, two different neural network forecasting models: a back-propagation neural network (BPNN) and a genetic algorithm optimized backpropagation neural network (GABP) were established for comparative analysis. The foF2 parameters were forecasted under geomagnetic quiet and geomagnetic disturbed conditions during solar activity maximum (2015) and minimum (2019), respectively. The forecasting results of these models are compared with those of the international reference ionosphere model (IRI2016) and the measurements. The diurnal and seasonal variations of foF2 for the 4 models were compared and analyzed from 8 selected verification stations. The forecasting results reveal that the deep learning LSTM model presents the optimal performance of all models in forecasting the time series of foF2, while the IRI2016 model has the poorest forecasting performance, and the BPNN model and GABP model are between two of them. [ABSTRACT FROM AUTHOR]