Artificial forest (AF) is an effective means of human intervention in forest ecosystems, aiming at preventing issues, such as soil erosion and land desertification. However, owing to the characteristics of large-scale afforestation projects, which often involve vast spatial extents and extended temporal scales, AF usually exhibits complex distribution patterns. In such cases, traditional remote sensing methods usually fail to accurately monitor AF conditions. To address this issue, this study introduced deep learning (DL) algorithms to extract multilevel features from remote sensing images for AF mapping and employed image processing techniques to enhance AF boundary determination. Through integrating these two approaches, high-resolution mapping of AF parcels was generated for a typical region in the middle reach valley of the Yarlung Tsangpo River. In the validation phase, the extracted regions were compared with manually labeled datasets and three accuracy metrics were calculated to demonstrate the extraction performance of the model. The accuracy reached 90.12% with the intersection over union (IoU) of 88.42%, and the cross-entropy loss function is only 0.0218. Meanwhile, three sampling areas with different coverages were selected for comparison, and the extractions have better performance than the SAM model based on the comparison with the samples. The findings reveal that this method can segment each AF parcel into independent objects, and the results would be helpful for parcel-based researches.

Accurately determining the spatial position and distribution structure of agricultural cultivation parcels (ACPs) is essential for regional agricultural planning and food security. Currently, utilizing deep learning technology based on very high resolution remote sensing imagery has proven effective for intelligent parcel extraction. However, relying solely on the model output, especially from single-task models in mountainous regions with complex, heterogeneous, and fragmented smallholder agriculture, remains questionable. To address this challenge, leveraging geographical prior knowledge is critical. This article proposes using the deep semantic segmentation algorithm in conjunction with comprehensive prior strategies. An improved densely connected link network (D-LinkNet) is employed to delineate the parcels, while geographical zoning, coarse spatial scope, stratification strategy, and homogeneity checking are exerted to understand regions, facilitate samples, reduce interferences, decompose objects, and identify undersegmentation. The proposed framework was validated in Jiangjin district, Chongqing of China, using Gaofen-2 images as the vital data. Compared to the method relying solely on deep learning, our method achieved superior performance with an overall accuracy of 0.924, Kappa coefficient of 0.847,$F1$score of 0.921, and IoU exceeding 0.8. Moreover, the results demonstrated high accuracy in the individual geometric precision of parcel. Over 1.23 million parcels were identified, comprising 77% cultivated land and 23% garden land. The areal proportion of paddy fields, drylands, and pepper gardens approximated 1:1:1, consistent with statistical data. This method offers a feasible approach for finely extracting agricultural parcels.

Because of the primary role of land surface temperature (LST) in the physical processes of surface energy balance at local through global scales, dynamic, continuous, and seamless LST monitoring is constantly in urgent need. Thermal infrared (TIR) remote sensing serves as the most commonly used sources for LST retrieval owing to its relatively fine spatial-temporal resolution and presentable accuracy. However, limited by the inability to penetrate clouds, original TIR LST data suffers significantly from data missing problems. Furthermore, the view time of pixels along the scan line differs significantly for polar-orbiting satellites, exerting appreciable influence on the subsequent data applications. To cope with the above setbacks simultaneously, we proposed a practical reconstruction framework based on the inner physical connection between LST and solar radiation, which was accurately expressed by random forest regression model, with the consideration of various auxiliary environmental factors (i.e., elevation, slope, longitude, latitude, and surface reflectance). Taking the Tibetan Plateau (TP) as the study area, the proposed method was applied to generate spatially seamless and time-consistent LST products with the use of the Moderate Resolution Imaging Spectroradiometer (MODIS) Terra daytime LST product. From visual assessment, the reconstructed product exhibits ideal spatial-temporal continuity within the TP. Through the validation with in-situ observations from five different stations, the results show a higher consistency with ground measurements than the LST product from the Global Land Data Assimilation System (GLDAS) and other all-weather LST product, with an average improvement on RMSE of 1.06 K and 1.59 K under clear conditions, and 1.86 K and 2.72 K under cloudy conditions. The validation demonstrates that the proposed method is well applicable for all-weather LST reconstruction over a large-scale area with significant surface heterogeneity, which also shows good ability to remove the temporal inconsistency induced by satellite observations. Additionally, it can be reliably generalized to different areas with similar data requirements for its sufficient effectiveness and flexibility.

Deep learning networks have achieved great success in many areas, such as in large-scale image processing. They usually need large computing resources and time and process easy and hard samples inefficiently in the same way. Another undesirable problem is that the network generally needs to be retrained to learn new incoming data. Efforts have been made to reduce the computing resources and realize incremental learning by adjusting architectures, such as scalable effort classifiers, multi-grained cascade forest (gcForest), conditional deep learning (CDL), tree CNN, decision tree structure with knowledge transfer (ERDK), forest of decision trees with radial basis function (RBF) networks, and knowledge transfer (FDRK). In this article, a parallel multistage wide neural network (PMWNN) is presented. It is composed of multiple stages to classify different parts of data. First, a wide radial basis function (WRBF) network is designed to learn features efficiently in the wide direction. It can work on both vector and image instances and can be trained in one epoch using subsampling and least squares (LS). Second, successive stages of WRBF networks are combined to make up the PMWNN. Each stage focuses on the misclassified samples of the previous stage. It can stop growing at an early stage, and a stage can be added incrementally when new training data are acquired. Finally, the stages of the PMWNN can be tested in parallel, thus speeding up the testing process. To sum up, the proposed PMWNN network has the advantages of: 1) optimized computing resources; 2) incremental learning; and 3) parallel testing with stages. The experimental results with the MNIST data, a number of large hyperspectral remote sensing data, and different types of data in different application areas, including many image and nonimage datasets, show that the WRBF and PMWNN can work well on both image and nonimage data and have very competitive accuracy compared to learning models, such as stacked autoencoders, deep belief nets, support vector machine (SVM), multilayer perceptron (MLP), LeNet-5, RBF network, recently proposed CDL, broad learning, gcForest, ERDK, and FDRK.

Missing data reconstruction is a classical yet challenging problem in remote sensing images. Most current methods based on traditional convolutional neural network require supplementary data and can only handle one specific task. To address these limitations, we propose a novel generative adversarial network-based missing data reconstruction method in this letter, which is capable of various reconstruction tasks given only single source data as input. Two auxiliary patch-based discriminators are deployed to impose additional constraints on the local and global regions, respectively. In order to better fit the nature of remote sensing images, we introduce special convolutions and attention mechanism in a two-stage generator, thereby benefiting the tradeoff between accuracy and efficiency. Combining with perceptual and multiscale adversarial losses, the proposed model can produce coherent structure with better details. Qualitative and quantitative experiments demonstrate the uncompromising performance of the proposed model against multisource methods in generating visually plausible reconstruction results. Moreover, further exploration shows a promising way for the proposed model to utilize spatio-spectral-temporal information. The codes and models are available athttps://github.com/Oliiveralien/Inpainting-on-RSI.

The spatial downscaling of soil moisture (SM) provides a technical tool to solve the problem of coarse resolution of passive microwave products. However, conventional methods are developed based on the kilometer scale grid pixels of remote sensing images. The regular rough grids will lead to the mixing and uncertainty of SM information. In this paper, we formulate a novel land geoparcel-based spatial downscaling technique for the Soil Moisture Active Passive (SMAP) satellite products. It is developed by combining XGBoost (eXtreme Gradient Boosting) machine learning algorithm with the support of geoparcel vector data and a variety of auxiliary raster data. The downscaling effect is evaluated by using SMAP 9km products and site measured data in Tongnan District of Chongqing, China. The experiments show that the geoparcel-based downscaling method maintains the dynamic range of the original SM product, and conserves energy before and after downscaling. It is proved that our method effectively increases the spatial details of the original SM product with complete spatial coverage. The comparison and analysis with the ground verification data demonstrate that the formalized procedure with geoparcel-based spatial downscaling allows better results than those of using km-scale regular grids.

Object-based change detection (CD) is an effective method of identifying detailed changes in land features by contrastively observing the same areas of high-resolution remote sensing images at different times. Binarization is the important step in partitioning changed and unchanged classes in the unsupervised domain. We formulate a novel binarization technique based on the Weibull mixture model, where generated similarity measure images are modeled using a mixture of nonnormal Weibull distributions. The parameters in the model are further globally estimated by employing a genetic algorithm. Two data sets with high-resolution remote sensing images are used to evaluate the effectiveness of the proposed method. Experimental results demonstrate that the method allows better and more robust unsupervised object-based CD than do state-of-the-art threshold-based and clustering-based methods. Advantages of the proposed method are embodied in the modeling of relatively few data of the changed class with a skewed and long tail distribution.

This paper introduces a weighted total least squares (WTLS)-based estimator into image registration to deal with the coordinates of control points (CPs) that are of unequal accuracy. The performance of the estimator is investigated by means of simulation experiments using different coordinate errors. Comparisons with ordinary least squares (LS), total LS (TLS), scaled TLS, and weighted LS estimators are made. A novel adaptive weight determination scheme is applied to experiments with remotely sensed images. These illustrate the practicability and effectiveness of the proposed registration method by collecting CPs with different-sized errors from multiple reference images with different spatial resolutions. This paper concludes that the WTLS-based iteratively reweighted TLS method achieves a more robust estimation of model parameters and higher registration accuracy if heteroscedastic errors occur in both the coordinates of reference CPs and target CPs.