Search

The timely and accurate acquisition of information on the distribution of the crop planting structure in the Loess Plateau of eastern Gansu Province, one of the most important agricultural areas in Western China, is crucial for promoting fine management of agriculture and ensuring food security. This study uses multi-temporal high-resolution remote sensing images to determine optimal segmentation scales for various crops, employing the estimation of scale parameter 2 (ESP2) tool and the Ratio of Mean Absolute Deviation to Standard Deviation (RMAS) model. The Canny edge detection algorithm is then applied for multi-scale image segmentation. By incorporating crop phenological factors and using the L1-regularized logistic regression model, we optimized 39 spatial feature factors—including spectral, textural, geometric, and index features. Within a multi-level classification framework, the Random Forest (RF) classifier and Convolutional Neural Network (CNN) model are used to classify the cropping patterns in four test areas based on the multi-scale segmented images. The results indicate that integrating the Canny edge detection algorithm with the optimal segmentation scales calculated using the ESP2 tool and RMAS model produces crop parcels with more complete boundaries and better separability. Additionally, optimizing spatial features using the L1-regularized logistic regression model, combined with phenological information, enhances classification accuracy. Within the OBIC framework, the RF classifier achieves higher accuracy in classifying cropping patterns. The overall classification accuracies for the four test areas are 91.93%, 94.92%, 89.37%, and 90.68%, respectively. This paper introduced crop phenological factors, effectively improving the extraction precision of the shattered agricultural planting structure in the Loess Plateau of eastern Gansu Province. Its findings have important application value in crop monitoring, management, food security and other related fields. [ABSTRACT FROM AUTHOR]

The analysis of marine environmental parameters plays a significant role in various aspects, including sea surface target detection, the monitoring of the marine ecological environment, marine meteorology and disaster forecasting, and the monitoring of internal waves in the ocean. In particular, for sea surface target detection, the accurate and high-resolution input of marine environmental parameters is crucial for multi-scale sea surface modeling and the prediction of sea clutter characteristics. In this paper, based on the low-resolution wind speed, significant wave height, and wave period data provided by ECMWF for the surrounding seas of China (specified latitude and longitude range), a deep learning model based on a residual structure is proposed. By introducing an attention module, the model effectively addresses the poor modeling performance of traditional methods like nearest neighbor interpolation and linear interpolation at the edge positions in the image. Experimental results demonstrate that with the proposed approach, when the spatial resolution of wind speed increases from 0.5° to 0.25°, the results achieve a mean square error (MSE) of 0.713, a peak signal-to-noise ratio (PSNR) of 49.598, and a structural similarity index measure (SSIM) of 0.981. When the spatial resolution of the significant wave height increases from 1° to 0.5°, the results achieve a MSE of 1.319, a PSNR of 46.928, and an SSIM of 0.957. When the spatial resolution of the wave period increases from 1° to 0.5°, the results achieve a MSE of 2.299, a PSNR of 44.515, and an SSIM of 0.940. The proposed method can generate high-resolution marine environmental parameter data for the surrounding seas of China at any given moment, providing data support for subsequent sea surface modeling and for the prediction of sea clutter characteristics. [ABSTRACT FROM AUTHOR]

The accurate estimation of forest aboveground biomass is of great significance for forest management and carbon balance monitoring. Remote sensing instruments have been widely applied in forest parameters inversion with wide coverage and high spatiotemporal resolution. In this paper, the capability of different remote-sensed imagery was investigated, including multispectral images (GaoFen-6, Sentinel-2 and Landsat-8) and various SAR (Synthetic Aperture Radar) data (GaoFen-3, Sentinel-1, ALOS-2), in aboveground forest biomass estimation. In particular, based on the forest inventory data of Hangzhou in China, the Random Forest (RF), Convolutional Neural Network (CNN) and Convolutional Neural Networks Long Short-Term Memory Networks (CNN-LSTM) algorithms were deployed to construct the forest biomass estimation models, respectively. The estimate accuracies were evaluated under the different configurations of images and methods. The results show that for the SAR data, ALOS-2 has a higher biomass estimation accuracy than the GaoFen-3 and Sentinel-1. Moreover, the GaoFen-6 data is slightly worse than Sentinel-2 and Landsat-8 optical data in biomass estimation. In contrast with the single source, integrating multisource data can effectively enhance accuracy, with improvements ranging from 5% to 10%. The CNN-LSTM generally performs better than CNN and RF, regardless of the data used. The combination of CNN-LSTM and multisource data provided the best results in this case and can achieve the maximum R2 value of up to 0.74. It was found that the majority of the biomass values in the study area in 2018 ranged from 60 to 90 Mg/ha, with an average value of 64.20 Mg/ha. [ABSTRACT FROM AUTHOR]

Road extraction is crucial in urban planning, rescue operations, and military applications. Compared to traditional methods, using deep learning for road extraction from remote sensing images has demonstrated unique advantages. However, previous convolutional neural networks (CNN)-based road extraction methods have had limited receptivity and failed to effectively capture long-distance road features. On the other hand, transformer-based methods have good global information-capturing capabilities, but face challenges in extracting road edge information. Additionally, existing excellent road extraction methods lack validation for the Chinese region. To address these issues, this paper proposes a novel road extraction model called the global–local information fusion network (GLNet). In this model, the global information extraction (GIE) module effectively integrates global contextual relationships, the local information extraction (LIE) module accurately captures road edge information, and the information fusion (IF) module combines the output features from both global and local branches to generate the final extraction results. Further, a series of experiments on two different Chinese road datasets with geographic robustness demonstrate that our model outperforms the state-of-the-art deep learning models for road extraction tasks in China. On the CHN6-CUG dataset, the overall accuracy (OA) and intersection over union (IoU) reach 97.49% and 63.27%, respectively, while on the RDCME dataset, OA and IoU reach 98.73% and 84.97%, respectively. These research results hold significant implications for road traffic, humanitarian rescue, and environmental monitoring, particularly in the context of the Chinese region. [ABSTRACT FROM AUTHOR]

Gross floor area is defined as the product of number of building stories and its base area. Gross floor area acquisition is the core problem to estimate floor area ratio, which is an important indicator for many geographical analyses. High data acquisition cost or inherent defect of methods for existing gross floor area acquisition methods limit their applications in a wide range. In this paper we proposed three instance-wise gross floor area estimation methods in various degrees of end-to-end learning from monocular optical images based on the NoS R-CNN, which is a deep convolutional neural network to estimate the number of building stories. To the best of our knowledge, this is the first attempt to estimate instance-wise gross floor area from monocular optical satellite images. For comparing the performance of the proposed three methods, experiments on our dataset from nine cities in China were carried out, and the results were analyzed in detail in order to explore the reasons for the performance gap between the different methods. The results show that there is an inverse relationship between the model performance and the degree of end-to-end learning for base area estimation task and gross floor area estimation task. The quantitative and qualitative evaluations of the proposed methods indicate that the performances of proposed methods for accurate GFA estimation are promising for potential applications using large-scale remote sensing images. The proposed methods provide a new perspective for gross floor area/floor area ratio estimation and downstream tasks such as population estimation, living conditions assessment, etc. [ABSTRACT FROM AUTHOR]

In this paper, a method for joint sea surface rainfall intensity (RI), wind speed, and wave height retrieval based on spaceborne global navigation satellite system reflectometry (GNSS-R) data is proposed, which especially considers the effects between these two parameters. A method of rainfall detection (RD) according to different wind speed ranges is also proposed by mitigating the impact of swell and wind speed. The results, with data collected over the oceans near Southeast Asia, show that the RD method has a detection accuracy of up to 81.74%. The RI retrieval accuracy can reach about 2 mm/h by simultaneously correcting the effects of wind speed and swell. The accuracy of wind speed retrieval is improved by about 5% after removing rainfall interference through RD in advance. After considering the influence of wind speed and eliminating rainfall interference, the retrieval accuracy of significant wave height (SWH) is improved by about 18%. Finally, the deep convolutional neural network (DCNN) model is built to estimate the SWH of the swell. The results show that the retrieval accuracy of the swell height is better than 0.20 m after excluding rainfall interference. The proposed joint retrieval method provides an important reference for the future acquisition of multiple high-precision marine geophysical parameters by spaceborne GNSS-R technology. [ABSTRACT FROM AUTHOR]

In response to uncertainty in remotely sensed land cover products, there is continuing research on accuracy assessment and analysis. Given reference sample data, accuracy indicators are commonly estimated based on error matrices, from which areal extents of different cover types are also estimated. There are merits to explore the ways utilities of land cover products may be further enhanced beyond map face values and conventional area estimation. This paper presents an integrative method (CCAErrMat) for uncertainty characterization and utility enhancement. This works through reference-map cover type co-occurrence analyses based on error matrices localized in canonical correspondence analysis (CCA) ordination space rather than in geographic space to overcome the sparsity of reference sample data. The aforementioned co-occurrence analyses facilitate quantification of accuracy indicators, identification of correctly classified and perfectly misclassified pixels, and prediction of reference class probabilities, all at individual pixels. Moreover, these predicted reference class probabilities are used as auxiliary variables to formulate model-assisted area estimation, further enhancing map utilities. Extensions to CCAErrMat are also investigated as a way to bypass the pre-computing of map class occurrence pattern indices as candidate explanatory variables for CCAErrMat, leading to two variant methods: CCACCAErrMat and CNNCCAErrMat. A case study based in Wuhan municipality, central China was undertaken to compare the proposed method against alternative methods, including CCA-separate and CNN-separate. The advantages of CCAErrMat and CCACCAErrMat were confirmed. The proposed method is recommendable for characterizing uncertainty and enhancing utilities in land cover maps by analyzing locally constrained error matrices. The method is also cost-effective in terms of reference sample data, as requirements for them are similar to those for conventional accuracy assessments. [ABSTRACT FROM AUTHOR]

Timely and accurate crop yield information can ensure regional food security. In the field of predicting crop yields, deep learning techniques such as long short-term memory (LSTM) and convolutional neural networks (CNN) are frequently employed. Many studies have shown that the predictions of models combining the two are better than those of single models. Crop growth can be reflected by the vegetation index calculated using data from remote sensing. However, the use of pure remote sensing data alone ignores the spatial heterogeneity of different regions. In this paper, we tested a total of three models, CNN-LSTM, CNN and convolutional LSTM (ConvLSTM), for predicting the annual rice yield at the county level in Hubei Province, China. The model was trained by ERA5 temperature (AT) data, MODIS remote sensing data including the Enhanced Vegetation Index (EVI), Gross Primary Productivity (GPP) and Soil-Adapted Vegetation Index (SAVI), and a dummy variable representing spatial heterogeneity; rice yield data from 2000–2019 were employed as labels. Data download and processing were based on Google Earth Engine (GEE). The downloaded remote sensing images were processed into normalized histograms for the training and prediction of deep learning models. According to the experimental findings, the model that included a dummy variable to represent spatial heterogeneity had a stronger predictive ability than the model trained using just remote sensing data. The prediction performance of the CNN-LSTM model outperformed the CNN or ConvLSTM model. [ABSTRACT FROM AUTHOR]

Landslide disasters cause serious property losses and casualties every year. Landslide displacement prediction is fundamental for mitigating landslide disasters. Several approaches have been used to predict landslide displacement, yet a more accurate and reliable displacement prediction still has a poor understanding of landslide early warning systems for landslide mitigation, due to limited data and mutational displacements. To boost the robustness and accuracy of landslide displacement prediction, this paper assembled a new hybrid model containing the local mean decomposition (LMD), innovations state space models for exponential smoothing (ETS), and the temporal convolutional network (TCN). The proposed model, which is based on over 10 years of long-term time series monitoring GPS data, was tested on the selected case—stepwise Baijiabao landslide in the Three Gorges Reservoir area of China (TGRA) was tested by the proposed model. The results presented that the LMD–ETS–TCN model has the best performance in comparison with other benchmark models. Compared with autoregressive integrated moving average (ARIMA), support vector regression (SVR), and long short-term memory neural network (LSTM), the accuracy was noticeably improved by an average of 40.9%, 46.2%, and 22.1%, respectively. The robustness and effectiveness of the presented approach are attested, and it has discernible improvements for landslide displacement prediction. [ABSTRACT FROM AUTHOR]

Water conservancy personnel usually need to know the water level by water gauge images in real-time and with an expected accuracy. However, accurately recognizing the water level from water gauge images is still a complex problem. This article proposes a composite method applied in the Wuyuan City, Jiangxi Province, in China. This method can detect water gauge areas and number areas from complex and changeable scenes, accurately detect the water level line from various water gauges, and finally, obtain the accurate water level value. Firstly, FCOS is improved by fusing a contextual adjustment module to meet the requirements of edge computing and ensure considerable detection accuracy. Secondly, to deal with scenes with indistinct water level features, we also apply the contextual adjustment module for Deeplabv3+ to segment the water gauge area above the water surface. Then, the area can be used to obtain the position of the water level line. Finally, the results of the previous two steps are combined to calculate the water level value. Detailed experiments prove that this method solves the problem of water level recognition in complex hydrological scenes. Furthermore, the recognition error of the water level by this method is less than 1 cm, proving it is capable of being applied in real river scenes. [ABSTRACT FROM AUTHOR]

The study of cloud types is critical for understanding atmospheric motions and climate predictions; for example, accurately classified cloud products help improve meteorological predicting accuracies. However, the current satellite cloud classification methods generally analyze the threshold change in a single pixel and do not consider the relationship between the surrounding pixels. The classification development relies heavily on human recourses and does not fully utilize the data-driven advantages of computer models. Here, a new intelligent cloud classification method based on the U-Net network (CLP-CNN) is developed to obtain more accurate, higher frequency, and larger coverage cloud classification products. The experimental results show that the CLP-CNN network can complete a cloud classification task of 800 × 800 pixels in 0.9 s. The classification area covers most of China, and the classification task only needs to use the original L1-level data, which can meet the requirements of a real-time operation. With the Himawari-8 CLTYPE product and the CloudSat 2B-CLDCLASS product as the test comparison target, the CLP-CNN network results match the Himawari-8 product highly, by 84.4%. The probability of detection (POD) is greater than 0.83 for clear skies, deep-convection, and Cirrus–Stratus type clouds. The probability of detection (POD) and accuracy are improved compared with other deep learning methods. [ABSTRACT FROM AUTHOR]

Two-dimensional phase unwrapping (2-D PU) is vital for reconstructing Earth's surface topography and displacement from interferometric synthetic aperture radar (InSAR) data. Conventional algorithms rely on the postulate, but this assumption is often insufficient due to abrupt topographic changes and severe noise. To address this challenge, our research proposes a novel approach utilizing deep convolutional neural networks inspired by the U-Net architecture to estimate phase gradient information. Our approach involves downsampling the input data to extract crucial features, followed by upsampling to restore spatial resolution. We incorporate two attention mechanisms—feature pyramid attention (FPA) and global attention upsample (GAU)—and a residual structure in the network's structure. Thus, we construct ResDANet (residual and dual attention net). We rigorously train ResDANet utilizing simulated datasets and employ an L1-norm objective function to minimize the disparity between unwrapped phase gradients and those calculated by ResDANet, yielding the final 2-D PU results. The network is rigorously trained using two distinct training strategies and encompassing three types of simulated datasets. ResDANet exhibits excellent robust performance and efficiency on simulated data and real data, such as China's Three Gorges and an Italian volcano. [ABSTRACT FROM AUTHOR]

Since the early 1950s, the development of human settlements and over-exploitation of agriculture in the China side of the Amur River Basin (CARB) have had a major impact on the water environment of the surrounding lakes, resulting in a decrease of aquatic vegetation. According to the United Nations Sustainable Development Goals, a comprehensive understanding of the extent and variability of aquatic vegetation is crucial for preserving the structure and functionality of stable aquatic ecosystems. Currently, there is a deficiency in the CARB long-sequence dataset of aquatic vegetation distribution in China. This shortage hampers effective support for actual management. Therefore, the development of a fast, robust, and automatic method for accurate extraction of aquatic vegetation becomes crucial for large-scale applications. Our objective is to gather information on the spatial and temporal distribution as well as changes in aquatic vegetation within the CARB. Utilizing a hybrid approach that combines the maximum spectral index composite and Otsu algorithm, along with the integration of convolutional neural networks (CNN) and random forest, we applied this methodology to obtain an annual dataset of aquatic vegetation spanning from 1985 to 2020 using Landsat series imagery. The accuracy of this method was validated through both field investigations and Google Images. Upon assessing the confusion matrix spanning from 1985 to 2020, the producer accuracy for aquatic vegetation classification consistently exceeded 87%. Further quantitative analysis unveiled a discernible decreasing trend in both the water and vegetation areas of lakes larger than 20 km2 within the CARB over the past 36 years. Specifically, the total water area decreased from 3575 km2 to 3412 km2, while the vegetation area decreased from 745 km2 to 687 km2. These changes may be attributed to a combination of climate change and human activities. These quantitative data hold significant practical implications for establishing a scientific restoration path for lake aquatic vegetation. They are particularly valuable for constructing the historical background and reference indices of aquatic vegetation. [ABSTRACT FROM AUTHOR]

Landslide susceptibility assessment (LSA) is an essential tool for landslide hazard warning. The selection of earthquake-related factors is pivotal for seismic LSA. In this study, Newmark displacement (Dn) is employed as the earthquake-related factor, providing a detailed representation of seismic characteristics. On the algorithmic side, a dual-channel convolutional neural network (CNN) model is built, and the last classification layer is replaced with two machine learning (ML) models to facilitate the extraction of deeper features related to landslide development. This research focuses on Beichuan County in Sichuan Province, China. Fifteen landslide predisposing factors, including hydrological, geomorphic, geological, vegetation cover, anthropogenic, and earthquake-related features, were extensively collected. The results demonstrate some specific issues. Dn outperforms conventional earthquake-related factors such as peak ground acceleration (PGA) and Arias intensity (Ia) in capturing seismic influence on landslide development. Under the same conditions, the OA improved by 5.55% and AUC improved by 0.055 compared to the PGA; the OA improved by 3.2% and AUC improved by 0.0327 compared to the Ia. The improved CNN outperforms ML models. Under the same conditions, the OA improved by 4.69% and AUC improved by 0.0467 compared to RF; the OA improved by 4.47% and AUC improved by 0.0447 compared to SVM. Additionally, historical landslides validate the reasonableness of the landslide susceptibility maps. The proposed method exhibits a high rate of overlap with the historical landslide inventory. The proportion of historical landslides in the very high and high susceptibility zones exceeds 87%. The method not only enhances accuracy but also produces a more fine-grained susceptibility map, providing a reliable basis for early warning of seismic landslides. [ABSTRACT FROM AUTHOR]

Remote sensing image segmentation with samples imbalance is always one of the most important issues. Typically, a high-resolution remote sensing image has the characteristics of high spatial resolution and low spectral resolution, complex large-scale land covers, small class differences for some land covers, vague foreground, and imbalanced distribution of samples. However, traditional machine learning algorithms have limitations in deep image feature extraction and dealing with sample imbalance issue. In the paper, we proposed an improved full-convolution neural network, called DeepLab V3+, with loss function based solution of samples imbalance. In addition, we select Sentinel-2 remote sensing images covering the Yuli County, Bayingolin Mongol Autonomous Prefecture, Xinjiang Uygur Autonomous Region, China as data sources, then a typical region image dataset is built by data augmentation. The experimental results show that the improved DeepLab V3+ model can not only utilize the spectral information of high-resolution remote sensing images, but also consider its rich spatial information. The classification accuracy of the proposed method on the test dataset reaches 97.97%. The mean Intersection-over-Union reaches 87.74%, and the Kappa coefficient 0.9587. The work provides methodological guidance to sample imbalance correction, and the established data resource can be a reference to further study in the future. [ABSTRACT FROM AUTHOR]

Revealing the mechanism of hydrological and agricultural drought has been challenging and vital in the environment under extreme weather and water resource shortages. To explore the evolution process from meteorological to hydrological and agricultural drought further, multi-source remote sensing data, including the Gravity Recovery and Climate Experiment (GRACE) product, were collected in the Huaihe River basin of China during 2002–2020. Three machine learning methods, including long short-term memory neural network (LSTM), convolutional neural network (CNN), and categorical boosting (CatBoost), were constructed for hydrological and agricultural drought forecasting. The propagation time from meteorological drought to surface water storage and terrestrial water storage drought, evaluated by the standardized precipitation evapotranspiration index, was 8 and 11 months with Pearson correlation coefficients (R) of 0.68 and 0.48, respectively. Groundwater storage drought was correlated with evapotranspiration and vegetation growth with a 12-month lag time, respectively. In addition, vegetation growth was affected by the drought of soil moisture at depths ranging from 100 to 200 cm with an 8-month lag time with an R of −0.39. Although the forecasting performances of terrestrial water storage drought were better than those of groundwater storage drought and agricultural drought, CNN always performed better than LSTM and CatBoost models, with Nash–Sutclife efficiency values during testing ranging from 0.28 to 0.70, 0.26 to 0.33, and −0.10 to −0.40 for terrestrial water storage drought, groundwater storage drought, and agricultural drought at lead times of 0–3 months, respectively. Furthermore, splitting training and testing data at random significantly improved the performances of CNN and CatBoost methods for drought forecasting rather than in chronological order splitting for non-stationary data. [ABSTRACT FROM AUTHOR]

Landslide susceptibility mapping (LSM) is significant for landslide risk assessment. However, there remains no consensus on which method is optimal for LSM. This study implements a dynamic approach to landslide hazard mapping by integrating spatio-temporal probability analysis with time-varying ground deformation velocity derived from the MT-InSAR (Multi-Temporal InSAR) method. Reliable landslide susceptibility maps (LSMs) can inform landslide risk managers and government officials. First, sixteen factors were selected to construct a causal factor system for LSM. Next, Pearson correlation analysis, multicollinearity analysis, information gain ratio, and GeoDetector methods were applied to remove the least important factors of STI, plan curvature, TRI, and slope length. Subsequently, information quantity (IQ), logistic regression (LR), frequency ratio (FR), artificial neural network (ANN), random forest (RF), support vector machine (SVM), and convolutional neural network (CNN) methods were performed to construct the LSM. The results showed that the distance to a river, slope angle, distance from structure, and engineering geological rock group were the main factors controlling landslide development. A comprehensive set of statistical indicators was employed to evaluate these methods' effectiveness; sensitivity, F1-measure, and AUC (area under the curve) were calculated and subsequently compared to assess the performance of the methods. Machine learning methods' training and prediction accuracy were higher than those of statistical methods. The AUC values of the IQ, FR, LR, BP-ANN, RBF-ANN, RF, SVM, and CNN methods were 0.810, 0.854, 0.828, 0.895, 0.916, 0.932, 0.948, and 0.957, respectively. Although the performance order varied for other statistical indicators, overall, the CNN method was the best, while the BP-ANN and RBF-ANN method was the worst among the five examined machine methods. Hence, adopting the CNN approach in this study can enhance LSM accuracy, catering to the needs of planners and government agencies responsible for managing landslide-prone areas and preventing landslide-induced disasters. [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]

Agricultural greenhouses (AGs) are an important component of modern facility agriculture, and accurately mapping and dynamically monitoring their distribution are necessary for agricultural scientific management and planning. Semantic segmentation can be adopted for AG extraction from remote sensing images. However, the feature maps obtained by traditional deep convolutional neural network (DCNN)-based segmentation algorithms blur spatial details and insufficient attention is usually paid to contextual representation. Meanwhile, the maintenance of the original morphological characteristics, especially the boundaries, is still a challenge for precise identification of AGs. To alleviate these problems, this paper proposes a novel network called high-resolution boundary refined network (HBRNet). In this method, we design a new backbone with multiple paths based on HRNetV2 aiming to preserve high spatial resolution and improve feature extraction capability, in which the Pyramid Cross Channel Attention (PCCA) module is embedded to residual blocks to strengthen the interaction of multiscale information. Moreover, the Spatial Enhancement (SE) module is employed to integrate the contextual information of different scales. In addition, we introduce the Spatial Gradient Variation (SGV) unit in the Boundary Refined (BR) module to couple the segmentation task and boundary learning task, so that they can share latent high-level semantics and interact with each other, and combine this with the joint loss to refine the boundary. In our study, GaoFen-2 remote sensing images in Shouguang City, Shandong Province, China are selected to make the AG dataset. The experimental results show that HBRNet demonstrates a significant improvement in segmentation performance up to an IoU score of 94.89%, implying that this approach has advantages and potential for precise identification of AGs. [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]

To overcome the interference of noise on the exploration effectiveness of the controlled-source electromagnetic method (CSEM), we improved the deep learning algorithm by combining the denoising convolutional neural network (DnCNN) with the residual network (ResNet), and propose a method based on the residual denoising convolutional neural network (ResDnCNN) and shift-invariant sparse coding (SISC) for denoising CSEM data. Firstly, a sample library was constructed by adding simulated noises of different types and amplitudes to high-quality CSEM data collected. Then, the sample library was used for model training in the ResDnCNN, resulting in a network model specifically designed for denoising CSEM data. Subsequently, the trained model was employed to denoise the measured data, generating preliminary denoised data. Finally, the preliminary denoised data was processed using SISC to obtain the final denoised high-quality data. Comparative experiments with the ResNet, DnCNN, U-Net, and long short-term memory (LSTM) networks demonstrated the significant advantages of our proposed method. It effectively removed strong noise such as Gaussian, impulse, and square wave, resulting in an improvement of the signal-to-noise ratio by nearly 20 dB. Testing on CSEM data from Sichuan Province, China, showed that the apparent resistivity curves plotted using our method were smoother and more credible. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) image is an effective remote sensing data source for geographic surveys. However, accurate land cover mapping based on SAR image in areas of complex terrain has become a challenge due to serious geometric distortions and the inadequate separation ability of dual-polarization data. To address these issues, a new land cover mapping framework which is suitable for complex terrain is proposed based on Gaofen-3 data of ascending and descending orbits. Firstly, the geometric distortion area is determined according to the local incident angle, based on analysis of the SAR imaging mechanism, and the correct polarization information of the opposite track is used to compensate for the geometric distortion area, including layovers and shadows. Then, the dual orbital polarization characteristics (DOPC) and dual polarization radar vegetation index (DpRVI) of dual-pol SAR data are extracted, and the optimal feature combination is found by means of Jeffries–Matusita (J-M) distance analysis. Finally, the deep learning method 2D convolutional neural network (2D-CNN) is applied to classify the compensated images. The proposed method was applied to a mountainous region of the Danjiangkou ecological protection area in China. The accuracy and reliability of the method were experimentally compared using the uncompensated images and the images without DpRVI. Quantitative evaluation revealed that the proposed method achieved better performance in complex terrain areas, with an overall accuracy (OA) score of 0.93, and a Kappa coefficient score of 0.92. Compared with the uncompensated image, OA increased by 5% and Kappa increased by 6%. Compared with the images without DpRVI, OA increased by 4% and Kappa increased by 5%. In summary, the results demonstrate the importance of ascending and descending orbit data to compensate geometric distortion and reveal the effectiveness of optimal feature combination including DpRVI. Its simple and effective polarization information compensation capability can broaden the promising application prospects of SAR images. [ABSTRACT FROM AUTHOR]

With the development of deep learning and remote sensing technologies in recent years, many semantic segmentation methods based on convolutional neural networks (CNNs) have been applied to road extraction. However, previous deep learning-based road extraction methods primarily used RGB imagery as an input and did not take advantage of the spectral information contained in hyperspectral imagery. These methods can produce discontinuous outputs caused by objects with similar spectral signatures to roads. In addition, the images obtained from different Earth remote sensing sensors may have different spatial resolutions, enhancing the difficulty of the joint analysis. This work proposes the Multiscale Fusion Attention Network (MSFANet) to overcome these problems. Compared to traditional road extraction frameworks, the proposed MSFANet fuses information from different spectra at multiple scales. In MSFANet, multispectral remote sensing data is used as an additional input to the network, in addition to RGB remote sensing data, to obtain richer spectral information. The Cross-source Feature Fusion Module (CFFM) is used to calibrate and fuse spectral features at different scales, reducing the impact of noise and redundant features from different inputs. The Multiscale Semantic Aggregation Decoder (MSAD) fuses multiscale features and global context information from the upsampling process layer by layer, reducing information loss during the multiscale feature fusion. The proposed MSFANet network was applied to the SpaceNet dataset and self-annotated images from Chongzhou, a representative city in China. Our MSFANet performs better over the baseline HRNet by a large margin of +6.38 IoU and +5.11 F1-score on the SpaceNet dataset, +3.61 IoU and +2.32 F1-score on the self-annotated dataset (Chongzhou dataset). Moreover, the effectiveness of MSFANet was also proven by comparative experiments with other studies. [ABSTRACT FROM AUTHOR]

Our society's growing need for mineral resources brings with it the associated risk of degrading our natural environment as well as impacting on neighboring communities. To better manage this risk, especially for open-pit mine (OM) operations, new earth observation tools are required for more accurate baseline mapping and subsequent monitoring. The purpose of this paper is to propose an object-oriented open-pit mine mapping (OOMM) framework from Gaofen-2 (GF-2) high-spatial resolution satellite image (HSRSI), based on convolutional neural networks (CNNs). To better present the different land use categories (LUCs) in the OM area, a minimum heterogeneity criterion-based multi-scale segmentation method was used, while a mean area ratio method was applied to optimize the segmentation scale of each LUC. After image segmentation, three object-feature domains were obtained based on the GF-2 HSRSI: spectral, texture, and geometric features. Then, the gradient boosting decision tree and Pearson correlation coefficient were used as an object feature information reduction (FIR) method to recognize the distinguishing feature that describe open-pit mines (OMs). Finally, the CNN was used by combing the significant features to map the OM. In total, 105 OM sites were extracted from the interpretation of GF-2 HSRSIs and the boundary of each OM was validated by field work and used as inputs to evaluate the open-pit mine mapping (OMM) accuracy. The results revealed that: (1) the FIR tool made a positive impact on effective OMM; (2) by splitting the segmented objects into two groups, training and testing sets which are composed of 70% of the objects, and validation sets which are formed by the remaining 30% of the objects, then combing the selected feature subsets for training to achieve an overall accuracy (OA) of 90.13% and a Kappa coefficient (KC) of 0.88 of the whole datasets; (3) comparing the results of the state-of-the-art method, support vector machine (SVM), in OMM, the proposed framework outperformed SVM by more than 7.28% in OA, 8.64% in KC, 6.15% in producer accuracy of OM and by 9.31% in user accuracy of OM. To the best of our knowledge, it is the first time that OM information has been used through the integration of multiscale segmentation of HSRSI with the CNN to get OMM results. The proposed framework can not only provide reliable technical support for the scientific management and environmental monitoring of open pit mining areas, but also be of wide generality and be applicable to other kinds of land use mapping in mining areas using HSR images. [ABSTRACT FROM AUTHOR]

Runoff forecasting is important for water resource management. Although deep learning models have substantially improved the accuracy of runoff prediction, the temporal and feature dependencies between rainfall–runoff time series elements have not been effectively exploited. In this work, we propose a new hybrid deep learning model to predict hourly streamflow: SA-CNN-LSTM (self-attention, convolutional neural network, and long short-term memory network). The advantages of CNN and LSTM in terms of data extraction from time series data are combined with the self-attention mechanism. By considering interdependences of the rainfall–runoff sequence between timesteps and between features, the prediction performance of the model is enhanced. We explored the performance of the model in the Mazhou Basin, China; we compared its performance with the performances of LSTM, CNN, ANN (artificial neural network), RF (random forest), SA-LSTM, and SA-CNN. Our analysis demonstrated that SA-CNN-LSTM demonstrated robust prediction with different flood magnitudes and different lead times; it was particularly effective within lead times of 1–5 h. Additionally, the performance of the self-attention mechanism with LSTM and CNN alone, respectively, was improved at some lead times; however, the overall performance was unstable. In contrast, the hybrid model integrating CNN, LSTM, and the self-attention mechanism exhibited better model performance and robustness. Overall, this study considers the importance of temporal and feature dependencies in hourly runoff prediction, then proposes a hybrid deep learning model to improve the performances of conventional models in runoff prediction. [ABSTRACT FROM AUTHOR]

The local climate zone (LCZ) scheme is of great value for urban heat island (UHI) effect studies by providing a standard classification framework to describe the local physical structure at a global scale. In recent years, with the rapid development of satellite imaging techniques, both multi-spectral (MS) and synthetic aperture radar (SAR) data have been widely used in LCZ classification tasks. However, the fusion of MS and SAR data still faces the challenges of the different imaging mechanisms and the feature heterogeneity. In this study, to fully exploit and utilize the features of SAR and MS data, a data-grouping method was firstly proposed to divide multi-source data into several band groups according to the spectral characteristics of different bands. Then, a novel network architecture, namely Multi-source data Fusion Network for Local Climate Zone (MsF-LCZ-Net), was introduced to achieve high-precision LCZ classification, which contains a multi-branch CNN for multi-modal feature extraction and fusion, followed by a classifier for LCZ prediction. In the proposed multi-branch structure, a split–fusion-aggregate strategy was adopted to capture multi-level information and enhance the feature representation. In addition, a self channel attention (SCA) block was introduced to establish long-range spatial and inter-channel dependencies, which made the network pay more attention to informative features. Experiments were conducted on the So2Sat LCZ42 dataset, and the results show the superiority of our proposed method when compared with state-of-the-art methods. Moreover, the LCZ maps of three main cities in China were generated and analyzed to demonstrate the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

Currently, most deep learning (DL)-based models for precipitation forecasting face two conspicuous issues: the smoothing effect in the precipitation field and the degenerate effect of forecasting precipitation intensity. Therefore, this study proposes "time series residual convolution (TSRC)", a DL-based convolutional neural network for precipitation nowcasting over China with a lead time of 3 h. The core idea of TSRC is it compensates the current local cues with previous local cues during convolution processes, so more contextual information and less uncertain features would remain in deep networks. We use four years' radar echo reflectivity data from 2017 to 2020 for model training and one year's data from 2021 for model testing and compare it with two commonly used nowcasting models: optical flow model (OF) and UNet. Results show that TSRC obtains better forecasting performances than OF and UNet with a relatively high probability of detection (POD), low false alarm rate (FAR), small mean absolute error (MAE) and high structural similarity index (SSIM), especially at longer lead times. Meanwhile, the results of two case studies suggest that TSRC still introduces smoothing effects and slightly outperforms UNet at longer lead times. The most considerable result is that our model can forecast high-intensity radar echoes even for typhoon rainfall systems, suggesting that the degenerate effect of forecasting precipitation intensity can be improved by our model. Future works will focus on the combination of multi-source data and the design of the model's architecture to gain further improvements in precipitation short-term forecasting. [ABSTRACT FROM AUTHOR]

Laser-induced breakdown spectroscopy (LIBS) coupled with chemometrics is an efficient method for rock identification and classification, which has considerable potential in planetary geology. A great challenge facing the LIBS community is the difficulty to accurately discriminate rocks with close chemical compositions. A convolutional neural network (CNN) model has been designed in this study to identify twelve types of rock, among which some rocks have similar compositions. Both the training set and the testing set are constructed based on the LIBS spectra acquired by Mars Surface Composition Detector (MarSCoDe) for China's Tianwen-1 Mars exploration mission. All the spectra were collected from dedicated rock pellet samples, which were placed in a simulated Martian atmospheric environment. The classification performance of the CNN has been compared with that of three alternative machine learning algorithms, i.e., logistic regression (LR), support vector machine (SVM), and linear discriminant analysis (LDA). Among the four methods, it is on the CNN model that the highest classification correct rate has been obtained, as assessed by precision score, recall score, and the harmonic mean of precision and recall. Furthermore, the classification accuracy is inspected more quantitatively via Brier score, and the CNN is still the best performing model. The results demonstrate that the CNN-based chemometrics are an efficient tool for rock identification with LIBS spectra collected in a simulated Martian environment. Despite the relatively small sample set, this study implies that CNN-supported LIBS classification is a promising analytical technique for Tianwen-1 Mars mission and more planetary explorations in the future. [ABSTRACT FROM AUTHOR]

Deep learning-based semantic segmentation technology is widely applied in remote sensing and has achieved excellent performance in remote sensing image target extraction. Greenhouses play an important role in the development of agriculture in China. However, the rapid expansion of greenhouses has had a series of impacts on the environment. Therefore, the extraction of large-scale greenhouses is crucial for the sustainable development of agriculture and environmental governance. It is difficult for existing methods to acquire precise boundaries. Therefore, we propose a spatial convolutional long short-term memory structure, which can fully consider the spatial continuity of ground objects. We use multitask learning to improve the network's ability to extract image boundaries and promote convergence through auxiliary loss. We propose a superpixel optimization module to optimize the main-branch results of network semantic segmentation using more precise boundaries obtained by advanced superpixel segmentation techniques. Compared with other mainstream methods, our proposed structure can better consider spatial information and obtain more accurate results. We chose Shandong Province, China, as the study area and used Gaofen-1 satellite remote sensing images to create a new greenhouse dataset. Our method achieved an F1 score of 77%, a significant improvement over mainstream semantic segmentation networks, and it could extract greenhouse results with more precise boundaries. We also completed large-scale greenhouse mapping for Shandong Province, and the results show that our proposed modules have great potential in greenhouse extraction. [ABSTRACT FROM AUTHOR]

The spatial distribution of soil organic carbon (SOC) serves as critical geographic information for assessing ecosystem services, climate change mitigation, and optimal agriculture management. Digital mapping of SOC is challenging due to the complex relationships between the soil and its environment. Except for the well-known terrain and climate environmental covariates, vegetation that interacts with soils influences SOC significantly over long periods. Although several remote-sensing-based vegetation indices have been widely adopted in digital soil mapping, variables indicating long term vegetation growth have been less used. Vegetation phenology, an indicator of vegetation growth characteristics, can be used as a potential time series environmental covariate for SOC prediction. A CNN-LSTM model was developed for SOC prediction with inputs of static and dynamic environmental variables in Xuancheng City, China. The spatially contextual features in static variables (e.g., topographic variables) were extracted by the convolutional neural network (CNN), while the temporal features in dynamic variables (e.g., vegetation phenology over a long period of time) were extracted by a long short-term memory (LSTM) network. The ten-year phenological variables derived from moderate-resolution imaging spectroradiometer (MODIS) observations were adopted as predictors with historical temporal changes in vegetation in addition to the commonly used static variables. The random forest (RF) model was used as a reference model for comparison. Our results indicate that adding phenological variables can produce a more accurate map, as tested by the five-fold cross-validation, and demonstrate that CNN-LSTM is a potentially effective model for predicting SOC at a regional spatial scale with long-term historical vegetation phenology information as an extra input. We highlight the great potential of hybrid deep learning models, which can simultaneously extract spatial and temporal features from different types of environmental variables, for future applications in digital soil mapping. [ABSTRACT FROM AUTHOR]

The spatial pattern and temporal variation in paddy rice areas captured by remote sensing imagery provide an effective way of performing crop management and developing suitable agricultural policies. However, fragmented and scattered rice paddies due to undulating and varied topography, and the availability and quality of remote sensing images (e.g., frequent cloud coverage) pose significant challenges to accurate long-term rice mapping, especially for traditional pixel and phenological methods in subtropical monsoon regions. This study proposed a superpixel and deep-learning-based time series method to analyze Landsat time series data for paddy rice classification in complex landscape regions. First, a superpixel segmentation map was generated using a dynamic-time-warping-based simple non-iterative clustering algorithm with preprocessed spectral indices (SIs) time series data. Second, the SI images were overlaid onto the superpixel map to construct mean SIs time series for each superpixel. Third, a multivariate long short-term memory full convolution neural network (MLSTM-FCN) classifier was employed to learn time series features of rice paddies to produce accurate paddy rice maps. The method was evaluated using Landsat imagery from 2000 to 2020 in Cengong County, Guizhou Province, China. Results indicate that the superpixel MLSTM-FCN achieved a high performance with an overall accuracy varying from 0.9547 to 0.9721, which presents an 0.17–1.23% improvement compared to the random forest method. This study showed that combining spectral, spatial, and temporal features with deep learning methods can generate accurate paddy rice maps in complex landscape regions. [ABSTRACT FROM AUTHOR]

The continuous and extensive pinewood nematode disease has seriously threatened the sustainable development of forestry in China. At present, many studies have used high-resolution remote sensing images combined with a deep semantic segmentation algorithm to identify standing dead trees in the red attack period. However, due to the complex background, closely distributed detection scenes, and unbalanced training samples, it is difficult to detect standing dead trees (SDTs) in a variety of complex scenes by using conventional segmentation models. In order to further solve the above problems and improve the recognition accuracy, we proposed a new detection method called multi-scale spatial supervision convolutional network (MSSCN) to identify SDTs in a wide range of complex scenes based on airborne remote sensing imagery. In the method, a Gaussian kernel approach was used to generate a confidence map from SDTs marked as points for training samples, and a multi-scale spatial attention block was added into fully convolutional neural networks to reduce the loss of spatial information. Further, an augmentation strategy called copy–pasting was used to overcome the lack of efficient samples in this research area. Validation at four different forest areas belonging to two forest types and two diseased outbreak intensities showed that (1) the copy–pasting method helps to augment training samples and can improve the detecting accuracy with a suitable oversampling rate, and the best oversampling rate should be carefully determined by the input training samples and image data. (2) Based on the two-dimensional spatial Gaussian kernel distribution function and the multi-scale spatial attention structure, the MSSCN model can effectively find the dead tree extent in a confidence map, and by following this with maximum location searching we can easily locate the individual dead trees. The averaged precision, recall, and F1-score across different forest types and disease-outbreak-intensity areas can achieve 0.94, 0.84, and 0.89, respectively, which is the best performance among FCN8s and U-Net. (3) In terms of forest type and outbreak intensity, the MSSCN performs best in pure pine forest type and low-outbreak-intensity areas. Compared with FCN8s and U-Net, the MSSCN can achieve the best recall accuracy in all forest types and outbreak-intensity areas. Meanwhile, the precision metric is also maintained at a high level, which means that the proposed method provides a trade-off between the precision and recall in detection accuracy. [ABSTRACT FROM AUTHOR]

Most traditional methods have difficulty detecting landslide boundary accurately, and the existing methods based on deep learning often lead to insufficient training or overfitting due to insufficient samples. An end-to-end, semi-supervised adversarial network, which fully considers spectral and topographic features derived using unmanned aerial vehicle (UAV) photogrammetry, is proposed to extract landslides by semantic segmentation to address the abovementioned problem. In the generative network, a generator similar to pix2pix is introduced into the proposed adversarial nets to learn semantic features from UAV-photogrammetry-derived data by semi-supervised operation and a confrontational strategy to reduce the requirement of the number of labeled samples. In the discriminative network, DeepLabv3+ is improved by inserting multilevel skip connection architecture with upsampling operation to obtain the contextual information and retain the boundary information of landslides at all levels, and a topographic convolutional neural network is proposed to be inserted into the encoder to concatenate topographic features together with spectral features. Then, transfer learning with the pre-trained parameters and weights, shared with pix2pix and DeepLabv3+, is used to perform landslide extraction training and validation. In our experiments, the UAV-photogrammetry-derived data of a typical landslide located at Meilong gully in China are collected to test the proposed method. The experimental results show that our method can accurately detect the area of a landslide and achieve satisfactiory results based on several indicators including the Precision, Recall, F1 score, and mIoU, which are 13.07%, 15.65%, 16.96%, and 18.23% higher than those of the DeepLabV3+. Compared with state-of-the-art methods such as U-Net, PSPNet, and pix2pix, the proposed adversarial nets considering multidimensional information such as topographic factors can perform better and significantly improve the accuracy of landslide extraction. [ABSTRACT FROM AUTHOR]

Accurate and automatic identification of tree species information at the individual tree scale is of great significance for fine-scale investigation and management of forest resources and scientific assessment of forest ecosystems. Despite the fact that numerous studies have been conducted on the delineation of individual tree crown and species classification using drone high-resolution red, green and blue (RGB) images, and Light Detection and Ranging (LiDAR) data, performing the above tasks simultaneously has rarely been explored, especially in complex forest environments. In this study, we improve upon the state of the Mask region-based convolution neural network (Mask R-CNN) with our proposed attention complementary network (ACNet) and edge detection R-CNN (ACE R-CNN) for individual tree species identification in high-density and complex forest environments. First, we propose ACNet as the feature extraction backbone network to fuse the weighted features extracted from RGB images and canopy height model (CHM) data through an attention complementary module, which is able to selectively fuse weighted features extracted from RGB and CHM data at different scales, and enables the network to focus on more effective information. Second, edge loss is added to the loss function to improve the edge accuracy of the segmentation, which is calculated through the edge detection filter introduced in the Mask branch of Mask R-CNN. We demonstrate the performance of ACE R-CNN for individual tree species identification in three experimental areas of different tree species in southern China with precision (P), recall (R), F1-score, and average precision (AP) above 0.9. Our proposed ACNet–the backbone network for feature extraction–has better performance in individual tree species identification compared with the ResNet50-FPN (feature pyramid network). The addition of the edge loss obtained by the Sobel filter further improves the identification accuracy of individual tree species and accelerates the convergence speed of the model training. This work demonstrates the improved performance of ACE R-CNN for individual tree species identification and provides a new solution for tree-level species identification in complex forest environments, which can support carbon stock estimation and biodiversity assessment. [ABSTRACT FROM AUTHOR]

Mu Us Sandy Land is a typical semi-arid vulnerable ecological zone, characterized by vegetation degradation and severe desertification. Effectively identifying desertification changes has been a topical environmental issue in China. However, most previous studies have used a single method or remote sensing index to monitor desertification, and lacked an efficient and high-precision monitoring system. In this study, an optimal monitoring scheme that considers multiple indicators combination and different machine learning methods (Classification and Regression Tree-Decision Tree, CART-DT; Random Forest, RF; Convolutional Neural Networks, CNN) was developed and used to analyze the spatial–temporal patterns of desertification from 2000 to 2018 in Mu Us Sandy Land. The results showed that: (a) The random forest model performed best for monitoring desertification based on medium and low-resolution remote sensing images, and the four-index combination (Albedo, NDVI, LST and TGSI) obtained the highest classification accuracy (OA = 87.67%) in Mu Us Sandy Land. Surprisingly, the model accuracy of the three-index combination (NDVI, LST and TGSI) (OA = 85.74%) is comparable to the four-index combination. (b) The TGSI index used to characterize soil information performs well, while the LST is not conducive to the extraction of desertified land in several desertification monitoring indicators. (c) Since 2000, the area of extremely severe desertified land has shown a reversal trend; however, there is significant interannual fluctuation in the total and light desertification land area affected by extreme climate. This research provides a novel approach and a valuable reference for monitoring the evolution of desertification in regional studies, and the results improve the research system of desertification and provide a data basis for desertification cause analysis and prevention. [ABSTRACT FROM AUTHOR]

Having a high-quality historical air pollutant dataset is critical for environmental and epidemiological research. In this study, a novel deep learning model based on convolutional neural network architecture was developed to estimate ground-level ozone concentrations across eastern China. A high-resolution maximum daily average 8-h (MDA8) surface ground ozone concentration dataset was generated with the support of the total ozone column from the satellite Tropospheric Monitoring Instrument, meteorological data from the China Meteorological Administration Land Data Assimilation System, and simulations of the WRF-Chem model. The modeled results were compared with in situ measurements in five cities that were not involved in model training, and the mean R2 of predicted ozone with observed values was 0.9, indicating the good robustness of our model. In addition, we compared the model results with some widely used machine learning techniques (e.g., random forest) and recently published ozone datasets, showing that the accuracy of our model is higher and that the spatial distributions of predicted ozone are more coherent. This study provides an efficient and exact method to estimate ground-level ozone and offers a new perspective for modeling spatiotemporal air pollutants. [ABSTRACT FROM AUTHOR]

In recent decades, lithological mapping techniques using hyperspectral remotely sensed imagery have developed rapidly. The processing chains using visible-near infrared (VNIR) and shortwave infrared (SWIR) hyperspectral data are proven to be available in practice. The thermal infrared (TIR) portion of the electromagnetic spectrum has considerable potential for mineral and lithology mapping. In particular, the abovementioned rocks at wavelengths of 8–12 μm were found to be discriminative, which can be seen as a characteristic to apply to lithology classification. Moreover, it was found that most of the lithology mapping and classification for hyperspectral thermal infrared data are still carried out by traditional spectral matching methods, which are not very reliable due to the complex diversity of geological lithology. In recent years, deep learning has made great achievements in hyperspectral imagery classification feature extraction. It usually captures abstract features through a multilayer network, especially convolutional neural networks (CNNs), which have received more attention due to their unique advantages. Hence, in this paper, lithology classification with CNNs was tested on thermal infrared hyperspectral data using a Thermal Airborne Spectrographic Imager (TASI) at three small sites in Liuyuan, Gansu Province, China. Three different CNN algorithms, including one-dimensional CNN (1-D CNN), two-dimensional CNN (2-D CNN) and three-dimensional CNN (3-D CNN), were implemented and compared to the six relevant state-of-the-art methods. At the three sites, the maximum overall accuracy (OA) based on CNNs was 94.70%, 96.47% and 98.56%, representing improvements of 22.58%, 25.93% and 16.88% over the worst OA. Meanwhile, the average accuracy of all classes (AA) and kappa coefficient (kappa) value were consistent with the OA, which confirmed that the focal method effectively improved accuracy and outperformed other methods. [ABSTRACT FROM AUTHOR]

Land use and land cover change (LUCC) modeling has continuously been a major research theme in the field of land system science, which interprets the causes and consequences of land use dynamics. In particular, models that can obtain long-term land use data with high precision are of great value in research on global environmental change and climate impact, as land use data are important model input parameters for evaluating the effect of human activity on nature. However, the accuracy of existing reconstruction and prediction models is inadequate. In this context, this study proposes an integrated convolutional neural network (CNN) LUCC reconstruction and prediction model (CLRPM), which meets the demand for fine-scale LUCC reconstruction and prediction. This model applies the deep learning method, which far exceeds the performance of traditional machine learning methods, and uses CNN to extract spatial features and provide greater proximity information. Taking Baicheng city in Northeast China as an example, we verify that CLRPM achieved high-precision annual LUCC reconstruction and prediction, with an overall accuracy rate 9.38% higher than that of the existing models. Additionally, the error rate was reduced by 49.5%. Moreover, this model can perform multilevel LUCC classification category reconstructions and predictions. This study casts light on LUCC models within the high-precision and fine-grained LUCC categories, which will aid LUCC analyses and help decision-makers better understand complex land-use systems and develop better land management strategies. [ABSTRACT FROM AUTHOR]

Fully convolutional networks (FCN) such as UNet and DeepLabv3+ are highly competitive when being applied in the detection of earthquake-damaged buildings in very high-resolution (VHR) remote sensing images. However, existing methods show some drawbacks, including incomplete extraction of different sizes of buildings and inaccurate boundary prediction. It is attributed to a deficiency in the global context-aware and inaccurate correlation mining in the spatial context as well as failure to consider the relative positional relationship between pixels and boundaries. Hence, a detection method for earthquake-damaged buildings based on the object contextual representations (OCR) and boundary enhanced loss (BE loss) was proposed. At first, the OCR module was separately embedded into high-level feature extractions of the two networks DeepLabv3+ and UNet in order to enhance the feature representation; in addition, a novel loss function, that is, BE loss, was designed according to the distance between the pixels and boundaries to force the networks to pay more attention to the learning of the boundary pixels. Finally, two improved networks (including OB-DeepLabv3+ and OB-UNet) were established according to the two strategies. To verify the performance of the proposed method, two benchmark datasets (including YSH and HTI) for detecting earthquake-damaged buildings were constructed according to the post-earthquake images in China and Haiti in 2010, respectively. The experimental results show that both the embedment of the OCR module and application of BE loss contribute to significantly increasing the detection accuracy of earthquake-damaged buildings and the two proposed networks are feasible and effective. [ABSTRACT FROM AUTHOR]

Plastic greenhouses (PGs) are widely built near cities in China to produce vegetables and fruits. In order to promote sustainable agriculture, rural landscape construction, and better manage water resources, numerous remote sensing methods have been developed to identify and monitor the distribution of PGs, of which many map PGs based on spectral responses and geometric shapes. In this study, we proposed a new fine- and coarse-scale mapping approach using two-temporal Sentinel-2 images with various seasonal characteristics and a one-dimensional convolutional neural network (1D-CNN). Having applied this approach in a pilot area study, the results were summarized as follows: (1) A time-series analysis of Sentinel-2 images showed that the reflectance of greenhouses changes during crop growth and development. In particular, the red-edge and near-infrared bands undergo a significant increase and then decrease during the whole crop growth period. Thus, two critical period images, containing a substantial difference in greenhouse reflectance, were sufficient to carry out an accurate and efficient mapping result. (2) The 1D-CNN classifier was used to map greenhouses by capturing subtle details and the overall trend of the spectrum curve. Overall, our approach showed higher classification accuracy than other approaches using support vector machines (SVM) or random forests (RF). In addition, the greenhouse area identified was highly consistent with the existing surfaces observed in very high-resolution images, with a kappa co-efficient of 0.81. (3) The narrow band feature differences (red-edge and near infrared narrow bands) in two-temporal Sentinel-2 images played a significant role in high-precision greenhouse mapping. The classification accuracy with narrow band features was much better than the maps produced without narrow band features. This scheme provided a method to digitize greenhouse precisely and publish its statistics for free, which enable advanced decision support for agriculture management. [ABSTRACT FROM AUTHOR]

Accurate crop type maps play an important role in food security due to their widespread applicability. Optical time series data (TSD) have proven to be significant for crop type mapping. However, filling in missing information due to clouds in optical imagery is always needed, which will increase the workload and the risk of error transmission, especially for imagery with high spatial resolution. The development of optical imagery with high temporal and spatial resolution and the emergence of deep learning algorithms provide solutions to this problem. Although the one-dimensional convolutional neural network (1D CNN), long short-term memory (LSTM), and gate recurrent unit (GRU) models have been used to classify crop types in previous studies, their ability to identify crop types using optical TSD with missing information needs to be further explored due to their different mechanisms for handling invalid values in TSD. In this research, we designed two groups of experiments to explore the performances and characteristics of the 1D CNN, LSTM, GRU, LSTM-CNN, and GRU-CNN models for crop type mapping using unfilled Sentinel-2 (Sentinel-2) TSD and to discover the differences between unfilled and filled Sentinel-2 TSD based on the same algorithm. A case study was conducted in Hengshui City, China, of which 70.3% is farmland. The results showed that the 1D CNN, LSTM-CNN, and GRU-CNN models achieved acceptable classification accuracies (above 85%) using unfilled TSD, even though the total missing rate of the sample values was 43.5%; these accuracies were higher and more stable than those obtained using filled TSD. Furthermore, the models recalled more samples on crop types with small parcels when using unfilled TSD. Although LSTM and GRU models did not attain accuracies as high as the other three models using unfilled TSD, their results were almost close to those with filled TSD. This research showed that crop types could be identified by deep learning features in Sentinel-2 dense time series images with missing information due to clouds or cloud shadows randomly, which avoided spending a lot of time on missing information reconstruction. [ABSTRACT FROM AUTHOR]

This study proposed a new hybrid model based on the convolutional neural network (CNN) for making effective use of historical datasets and producing a reliable landslide susceptibility map. The proposed model consists of two parts; one is the extraction of landslide spatial information using two-dimensional CNN and pixel windows, and the other is to capture the correlated features among the conditioning factors using one-dimensional convolutional operations. To evaluate the validity of the proposed model, two pure CNN models and the previously used methods of random forest and a support vector machine were selected as the benchmark models. A total of 621 earthquake-triggered landslides in Ludian County, China and 14 conditioning factors derived from the topography, geological, hydrological, geophysical, land use and land cover data were used to generate a geospatial dataset. The conditioning factors were then selected and analyzed by a multicollinearity analysis and the frequency ratio method. Finally, the trained model calculated the landslide probability of each pixel in the study area and produced the resultant susceptibility map. The results indicated that the hybrid model benefitted from the features extraction capability of the CNN and achieved high-performance results in terms of the area under the receiver operating characteristic curve (AUC) and statistical indices. Moreover, the proposed model had 6.2% and 3.7% more improvement than the two pure CNN models in terms of the AUC, respectively. Therefore, the proposed model is capable of accurately mapping landslide susceptibility and providing a promising method for hazard mitigation and land use planning. Additionally, it is recommended to be applied to other areas of the world. [ABSTRACT FROM AUTHOR]

Mangroves play an important role in many aspects of ecosystem services. Mangroves should be accurately extracted from remote sensing imagery to dynamically map and monitor the mangrove distribution area. However, popular mangrove extraction methods, such as the object-oriented method, still have some defects for remote sensing imagery, such as being low-intelligence, time-consuming, and laborious. A pixel classification model inspired by deep learning technology was proposed to solve these problems. Three modules in the proposed model were designed to improve the model performance. A multiscale context embedding module was designed to extract multiscale context information. Location information was restored by the global attention module, and the boundary of the feature map was optimized by the boundary fitting unit. Remote sensing imagery and mangrove distribution ground truth labels obtained through visual interpretation were applied to build the dataset. Then, the dataset was used to train deep convolutional neural network (CNN) for extracting the mangrove. Finally, comparative experiments were conducted to prove the potential for mangrove extraction. We selected the Sentinel-2A remote sensing data acquired on 13 April 2018 in Hainan Dongzhaigang National Nature Reserve in China to conduct a group of experiments. After processing, the data exhibited 2093 × 2214 pixels, and a mangrove extraction dataset was generated. The dataset was made from Sentinel-2A satellite, which includes five original bands, namely R, G, B, NIR, and SWIR-1, and six multispectral indices, namely normalization difference vegetation index (NDVI), modified normalized difference water index (MNDWI), forest discrimination index (FDI), wetland forest index (WFI), mangrove discrimination index (MDI), and the first principal component (PCA1). The dataset has a total of 6400 images. Experimental results based on datasets show that the overall accuracy of the trained mangrove extraction network reaches 97.48%. Our method benefits from CNN and achieves a more accurate intersection and union ratio than other machine learning and pixel classification methods by analysis. The designed model global attention module, multiscale context embedding, and boundary fitting unit are helpful for mangrove extraction. [ABSTRACT FROM AUTHOR]

Mapping new and old buildings are of great significance for understanding socio-economic development in rural areas. In recent years, deep neural networks have achieved remarkable building segmentation results in high-resolution remote sensing images. However, the scarce training data and the varying geographical environments have posed challenges for scalable building segmentation. This study proposes a novel framework based on Mask R-CNN, named Histogram Thresholding Mask Region-Based Convolutional Neural Network (HTMask R-CNN), to extract new and old rural buildings even when the label is scarce. The framework adopts the result of single-object instance segmentation from the orthodox Mask R-CNN. Further, it classifies the rural buildings into new and old ones based on a dynamic grayscale threshold inferred from the result of a two-object instance segmentation task where training data is scarce. We found that the framework can extract more buildings and achieve a much higher mean Average Precision (mAP) than the orthodox Mask R-CNN model. We tested the novel framework's performance with increasing training data and found that it converged even when the training samples were limited. This framework's main contribution is to allow scalable segmentation by using significantly fewer training samples than traditional machine learning practices. That makes mapping China's new and old rural buildings viable. [ABSTRACT FROM AUTHOR]

Although efforts and progress have been made in crop classification using optical remote sensing images, it is still necessary to make full use of the high spatial, temporal, and spectral resolutions of remote sensing images. However, with the increasing volume of remote sensing data, a key emerging issue in the field of crop classification is how to find useful information from massive data to balance classification accuracy and processing time. To address this challenge, we developed a novel crop classification method, combining optimal feature selection (OFSM) with hybrid convolutional neural network-random forest (CNN-RF) networks for multi-temporal optical remote sensing images. This research used 234 features including spectral, segmentation, color, and texture features from three scenes of Sentinel-2 images to identify crop types in the Jilin province of northeast China. To effectively extract the effective features of remote sensing data with lower time requirements, the use of OFSM was proposed with the results compared with two traditional feature selection methods (TFSM): random forest feature importance selection (RF-FI) and random forest recursive feature elimination (RF-RFE). Although the time required for OFSM was 26.05 s, which was between RF-FI with 1.97 s and RF-RFE with 132.54 s, OFSM outperformed RF-FI and RF-RFE in terms of the overall accuracy (OA) of crop classification by 4% and 0.3%, respectively. On the basis of obtaining effective feature information, to further improve the accuracy of crop classification we designed two hybrid CNN-RF networks to leverage the advantages of one-dimensional convolution (Conv1D) and Visual Geometry Group (VGG) with random forest (RF), respectively. Based on the selected optimal features using OFSM, four networks were tested for comparison: Conv1D-RF, VGG-RF, Conv1D, and VGG. Conv1D-RF achieved the highest OA at 94.27% as compared with VGG-RF (93.23%), Conv1D (92.59%), and VGG (91.89%), indicating that the Conv1D-RF method with optimal feature input provides an effective and efficient method of time series representation for multi-temporal crop-type classification. [ABSTRACT FROM AUTHOR]

Tea is an important economic plant, which is widely cultivated in many countries, particularly in China. Accurately mapping tea plantations is crucial in the operations, management, and supervision of the growth and development of the tea industry. We propose an object-based convolutional neural network (CNN) to extract tea plantations from very high resolution remote sensing images. Image segmentation was performed to obtain image objects, while a fine-tuned CNN model was used to extract deep image features. We conducted feature selection based on the Gini index to reduce the dimensionality of deep features, and the selected features were then used for classifying tea objects via a random forest. The proposed method was first applied to Google Earth images and then transferred to GF-2 satellite images. We compared the proposed classification with existing methods: Object-based classification using random forest, Mask R-CNN, and object-based CNN without fine-tuning. The results show the proposed method achieved a higher classification accuracy than other methods and produced smaller over- and under-classification geometric errors than Mask R-CNN in terms of shape integrity and boundary consistency. The proposed approach, trained using Google Earth images, achieved comparable results when transferring to the classification of tea objects from GF-2 images. We conclude that the proposed method is effective for mapping tea plantations using very high-resolution remote sensing images even with limited training samples and has huge potential for mapping tea plantations in large areas. [ABSTRACT FROM AUTHOR]

Rice is an important agricultural crop in the Southwest Hilly Area, China, but there has been a lack of efficient and accurate monitoring methods in the region. Recently, convolutional neural networks (CNNs) have obtained considerable achievements in the remote sensing community. However, it has not been widely used in mapping a rice paddy, and most studies lack the comparison of classification effectiveness and efficiency between CNNs and other classic machine learning models and their transferability. This study aims to develop various machine learning classification models with remote sensing data for comparing the local accuracy of classifiers and evaluating the transferability of pretrained classifiers. Therefore, two types of experiments were designed: local classification experiments and model transferability experiments. These experiments were conducted using cloud-free Sentinel-2 multi-temporal data in Banan District and Zhongxian County, typical hilly areas of Southwestern China. A pure pixel extraction algorithm was designed based on land-use vector data and a Google Earth Online image. Four convolutional neural network (CNN) algorithms (one-dimensional (Conv-1D), two-dimensional (Conv-2D) and three-dimensional (Conv-3D_1 and Conv-3D_2) convolutional neural networks) were developed and compared with four widely used classifiers (random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM) and multilayer perceptron (MLP)). Recall, precision, overall accuracy (OA) and F1 score were applied to evaluate classification accuracy. The results showed that Conv-2D performed best in local classification experiments with OA of 93.14% and F1 score of 0.8552 in Banan District, OA of 92.53% and F1 score of 0.8399 in Zhongxian County. CNN-based models except Conv-1D provided more desirable performance than non-CNN classifiers. Besides, among the non-CNN classifiers, XGBoost received the best result with OA of 89.73% and F1 score of 0.7742 in Banan District, SVM received the best result with OA of 88.57% and F1 score of 0.7538 in Zhongxian County. In model transferability experiments, almost all CNN classifiers had low transferability. RF and XGBoost models have achieved acceptable F1 scores for transfer (RF = 0.6673 and 0.6469, XGBoost = 0.7171 and 0.6709, respectively). [ABSTRACT FROM AUTHOR]