The formation of black-odor water in urban rivers has a long history. It not only seriously affects the image of the city, but also easily breeds germs and damages the urban habitat. The prevention and treatment of urban black-odor water have long been important topics nationwide. “Action Plan for Prevention and Control of Water Pollution” issued by the State Council shows Chinese government’s high attention to this issue. However, treatment and monitoring are inextricably linked. There are few studies on the large-scale monitoring of black-odor water, especially the cases of using unmanned aerial vehicle (UAV) to efficiently and accurately monitor the spatial distribution of urban river pollution. Therefore, in order to get rid of the limitations of traditional ground sampling to evaluate the point source pollution of rivers, the UAV-borne hyperspectral imagery was applied in this paper. It is hoped to grasp the pollution status of the entire river as soon as possible from the surface. However, the retrieval of multiple water quality parameters will lead to cumulative errors, so the Nemerow comprehensive pollution index (NCPI) is introduced to characterize the pollution level of urban water. In the paper, the retrieval results of six regression models including gradient boosting decision tree regression (GBDTR) were compared, trying to find a regression model for the retrieval NCPI in the current scenario. In the first study area, the retrieval accuracy of the training dataset (adjusted_R² = 0.978), and test dataset (adjusted_R² = 0.974) was higher than that of the other regression models. Although the retrieval effect of random forest is similar to that of GBDTR in both training accuracy and image inversion, it is more computationally expensive. Finally, the spatial distribution graphs of NCPI and its technical feasibility in monitoring pollution sources were investigated, in combination with field observations.

Density-based spatial clustering of applications with noise (DBSCAN) is a density-based clustering algorithm that has the characteristics of being able to discover clusters of any shape, effectively distinguishing noise points and naturally supporting spatial databases. DBSCAN has been widely used in the field of spatial data mining. This paper studies the parallelization design and realization of the DBSCAN algorithm based on the Spark platform, and solves the following problems that arise when computing macro data: the requirement of a great deal of calculation using the single-node algorithm; the low level of resource-utilization with the multi-node algorithm; the large time consumption; and the lack of instantaneity. The experimental results indicate that the proposed parallel algorithm design is able to achieve more stable speedup at an increased involved spatial data scale.

Spatial features retrieved from satellite data play an important role for improving crop classification. In this study, we proposed a deep-learning-based time-series analysis method to extract and organize spatial features to improve parcel-based crop classification using high-resolution optical images and multi-temporal synthetic aperture radar (SAR) data. Central to this method is the use of multiple deep convolutional networks (DCNs) to extract spatial features and to use the long short-term memory (LSTM) network to organize spatial features. First, a precise farmland parcel map was delineated from optical images. Second, hundreds of spatial features were retrieved using multiple DCNs from preprocessed SAR images and overlaid onto the parcel map to construct multivariate time-series of crop growth for parcels. Third, LSTM-based network structures for organizing these time-series features were constructed to produce a final parcel-based classification map. The method was applied to a dataset of high-resolution ZY-3 optical images and multi-temporal Sentinel-1A SAR data to classify crop types in the Hunan Province of China. The classification results, showing an improvement of greater than 5.0% in overall accuracy relative to methods without spatial features, demonstrated the effectiveness of the proposed method in extracting and organizing spatial features for improving parcel-based crop classification.

Change detection is an increasingly important research topic in remote sensing application. Previous studies achieved land cover change detection (LCCD) using bi-temporal remote sensing images. However, many widely used methods detected change depending on a series of parameters, and determining parameters is time-consuming. Furthermore, numerous methods are data-dependent. Therefore, their degree of automation should be improved significantly. Three techniques, which consist of a semi-automatic change detection system, are proposed for LCCD to overcome the abovementioned drawbacks. The three techniques are as follows: (1) change magnitude image (CMI) noise reduction is based on Gaussian filter (GF), which is coupled with OTSU for reducing CMI noise automatically using an iterative optimization strategy; (2) a method based on histogram curve fitting is suggested to predict the threshold range for parameter determination; and (3) a modified region growing algorithm is built for iteratively constructing the final change detection map. The detection accuracies of the proposed system are investigated through four experiments with different bi-temporal image scenes. Compared with several widely used change detection methods, the proposed system can be applied to detect land cover change with high accuracy and flexibility. This work is an attempt to provide a change detection system that is compatible with remote sensing images with high and median-low spatial resolution.

Semi-supervised learning is an effective technique to represent the intrinsic features of hyperspectral image (HSI), which can reduce the cost to obtain the labeled information of samples. However, traditional semi-supervised learning methods fail to consider multiple properties of HSI, which have restricted the discriminant performance of feature representation. In this paper, we introduce the hypergraph into semi-supervised leraning to reveal the complex multi-structures of HSI, and construct a semi-supervised discriminant hypergraph learning (SSDHL) method by designing an intraclass hypergraph and an interclass graph with the labeled samples. SSDHL constructs an unsupervised hypergraph with the unlabeled samples. In addition, a total scatter matrix is used to measure the distribution of the labeled and unlabeled samples. Then, a low-dimensional projection function is constructed to compact the properties of the intraclass hypergraph and the unsupervised hypergraph, and simultaneously separate the characteristics of the interclass graph and the total scatter matrix. Finally, according to the objective function, we can obtain the projection matrix and the low-dimensional features. Experiments on three HSI data sets (Botswana, KSC, and PaviaU) show that the proposed method can achieve better classification results compared with a few state-of-the-art methods. The results indicate that SSDHL can simultaneously utilize the labeled and unlabeled samples to represent the homogeneous properties and restrain the heterogeneous characteristics of HSI.

Forest canopy height plays an important role in forest resource management and conservation. The accurate estimation of forest canopy height on a large scale is important for forest carbon stock, biodiversity, and the carbon cycle. With the technological development of satellite-based LiDAR, it is possible to determine forest canopy height over a large area. However, the forest canopy height that is acquired by this technology is influenced by topography and climate, and the canopy height that is acquired in complex subtropical mountainous regions has large errors. In this paper, we propose a method for estimating forest canopy height by combining long-time series Landsat images with GEDI satellite-based LiDAR data, with Fujian, China, as the study area. This approach optimizes the quality of GEDI canopy height data in topographically complex areas by combining stand age and tree height, while retaining the advantage of fast and effective forest canopy height measurements with satellite-based LiDAR. In this study, the growth curves of the main forest types in Fujian were first obtained by using a large amount of forest survey data, and the LandTrendr algorithm was used to obtain the forest age distribution in 2020. The obtained forest age was then combined with the growth curves of each forest type in order to determine the tree height distribution. Finally, the obtained average tree heights were merged with the GEDI_V27 canopy height product in order to create a modified forest canopy height model (MGEDI_V27) with a 30 m spatial resolution. The results showed that the estimated forest canopy height had a mean of 15.04 m, with a standard deviation of 4.98 m. In addition, we evaluated the accuracy of the GEDI_V27 and the MGEDI_V27 using the sample dataset. The MGEDI_V27 had a higher accuracy (R² = 0.67, RMSE = 2.24 m, MAE = 1.85 m) than the GEDI_V27 (R² = 0.39, RMSE = 3.35 m, MAE = 2.41 m). R², RMSE, and MAE were improved by 71.79%, 33.13%, and 22.53%, respectively. We also produced a forest age distribution map of Fujian for the year 2020 and a forest disturbance map of Fujian for the past 32 years. The research results can provide decision support for forest ecological protection and management and for carbon sink analysis in Fujian.