Water quality monitoring is very important in agricultural catchments. UV–Vis spectrometry is widely used in place of traditional analytical methods because it is cost effective and fast and there is no chemical waste. In recent years, artificial neural networks have been extensively studied and used in various areas. In this study, we plan to simplify water quality monitoring with UV–Vis spectrometry and artificial neural networks. Samples were collected and immediately taken back to a laboratory for analysis. The absorption spectra of the water sample were acquired within a wavelength range from 200 to 800 nm. Convolutional neural network (CNN) and partial least squares (PLS) methods are used to calculate water parameters and obtain accurate results. The experimental results of this study show that both PLS and CNN methods may obtain an accurate result: linear correlation coefficient (R²) between predicted value and true values of TOC concentrations is 0.927 with PLS model and 0.953 with CNN model, R² between predicted value and true values of TSS concentrations is 0.827 with PLS model and 0.915 with CNN model. CNN method may obtain a better linear correlation coefficient (R²) even with small number of samples and can be used for online water quality monitoring combined with UV–Vis spectrometry in agricultural catchment.

As China’s largest freshwater lake and an important wintering ground for white cranes in Asia, the Poyang Lake wetland has unique ecological value. However, wetland cover types have changed dynamically and have attracted the attention of society and researchers over the past few decades. To obtain detailed knowledge and understanding of the long-term landcover dynamics of Poyang Lake and the associated driving forces, Landsat and HJ-1A/B images (31 images) were used to acquire classification and frequency maps of Poyang Lake in the dry season from 1973–2019 based on the random forest (RF) algorithm. In addition, the driving forces were discussed according to the Geodetector model. The results showed that the coverage of water and mudflat showed opposite trends from 1987–2019. Water and vegetation exhibited a significant decreasing trend from 1981–2003 and from 1996–2004 (p < 0.01), respectively. A phenomenon of vegetation expanding from west to east was found, and the expansion areas were mainly concentrated in the central zone of Poyang Lake, while vegetation in the northern mountainous area of Songmen (region 1) and eastern Songmen Mountain (region 2), showed a significantly expanded trend (R² > 0.6, p < 0.01) during the five-decade period. The year-long dominant distribution of water occurred mainly in the two deltas formed by the Raohe and Tongjin rivers and the Fuhe and Xinjiang rivers, with deep water. In the 1973–2003 and 2003–2019 periods, a total of 313.522 km² of water turned into swamp and mudflat and 478.453 km² of swamp and mudflat transitioned into vegetation, respectively. Elevation and temperature appeared to be the main factors affecting the regional wetland evolution in the dry season and should be considered in the management of Poyang Lake. The findings of this work provide detailed information for spatial–temporal landcover changes of Poyang Lake, which could help policymakers to formulate scientific and appropriate policies and achieve restoration of the Poyang Lake wetland.

Due to weathering and external forces, solar panels are subject to fouling and defects after a certain amount of time in service. These fouling and defects have direct adverse consequences such as low-power efficiency. Because solar power plants usually have large-scale photovoltaic (PV) panels, fast detection and location of fouling and defects across large PV areas are imperative. A drone-mounted infrared thermography system was designed and developed, and its ability to detect rapid fouling on large-scale PV panel systems was investigated. The infrared images were preprocessed using the $K$ neighbor mean filter, and the single PV module on each image was recognized and extracted. Combining the local and global detection method, suspicious sites were located precisely. The results showed the flexible drone-mounted infrared thermography system to have a strong ability to detect the presence and determine the position of PV fouling. Drone-mounted infrared thermography also has good technical feasibility and practical value in the detection of PV fouling detection.

An increasingly common requirement in remote sensing is the integration of hyperspectral data collected simultaneously from different sensors (and fore-optics) operating across different wavelength ranges. Data from one module are often relied on to correct information in the other, such as aerosol optical thickness (AOT) and columnar water vapor (CWV). This paper describes problems associated with this process and recommends an improved strategy for processing remote sensing data, collected from both visible to near-infrared and shortwave infrared modules, to retrieve accurate AOT, CWV, and surface reflectance values. This strategy includes a workflow for radiometric and spatial cross-calibration and a method to retrieve atmospheric parameters and surface reflectance based on a radiative transfer function. This method was tested using data collected with the Compact Airborne Spectrographic Imager (CASI) and SWIR Airborne Spectrographic Imager (SASI) from a site in Huailai County, Hebei Province, China. Various methods for retrieving AOT and CWV specific to this region were assessed. The results showed that retrieving AOT from the remote sensing data required establishing empirical relationships between 465.6 nm/659 nm and 2105 nm, augmented by ground-based reflectance validation data, and minimizing the merit function based on AOT@550 nm optimization. The paper also extends the second-order difference algorithm (SODA) method using Powell’s methods to optimize CWV retrieval. The resulting CWV image has fewer residual surface features compared with the standard methods. The derived remote sensing surface reflectance correlated significantly with the ground spectra of comparable vegetation, cement road and soil targets. Therefore, the method proposed in this paper is reliable enough for integrated atmospheric correction and surface reflectance retrieval from hyperspectral remote sensing data. This study provides a good reference for surface reflectance inversion that lacks synchronized atmospheric parameters.

Monitoring the spatio-temporal dynamics of the Eastern Plain Lake (EPL) is vital to the local environment and economy. However, due to the limitations and efficiency of traditional image formats in storing and processing large amounts of images and optimal threshold adjustments are often necessary for water/non-water separation based on traditional multi-band/spectral water indexes over large areas and in the long-term, previous studies have either been on a short period or mainly focused on water inundation dynamics of several lakes. To address these issues, a multi-dimensional dataset (MDD) storage format was used to efficiently organize more than ~7000 time series composite MODIS images. Furthermore, a universal normalized water index (UNWI) was developed based on full-spectrum information to simplify optimal threshold adjustments. Consequently, the present study analyzed the patterns of spatio-temporal water dynamic patterns and potential driving factors of inundation changes at large lakes (>5 km²) in the EPL during 2000–2020 through MDD and UNWI. In terms of annual inundation patterns, the numbers of lakes that experienced significant (p < 0.05) decreases (17 lakes) and increases (43 lakes) were highest for Class IV lakes among six geographical classes. Variation in intra-annual inundation in Classes I and II is correlated with consumption of chemical fertilizers (CCF), while precipitation accounted for the most change in lake area in Class III. This spatio-temporal analysis of lakes provides a necessary foundation for the sustainable development and continuous investigations of the EPL.

Total suspended sediments (TSS) are an important water quality indicator. The spatiotemporal distribution patterns of TSS concentrations in summer in the Peace-Athabasca Delta (PAD) remain unclear between 2000 and 2020. Among empirical and machine learning models, the random forest (RF) model exhibits the best performance for the PAD with a coefficient of determination, normalized root-means-square error, and relative root-mean-square error of 0.92, 7.51%, and 27.36%, respectively. Our study analyzes the spatiotemporal TSS distribution based on 21 years of Landsat remote sensing data and the RF model. The results showed that the TSS concentrations of the Peace River were elevated in 2000, 2016, 2019, and 2020. The long-term TSS concentration distribution in the PAD showed a decreasing trend from west to east, and the TSS concentrations ranged from 6 to 80 mg/L level and remained stable in Lake Athabasca during the investigated period. Moreover, 57.14% of the PAD area exhibited no significant change between 2000 and 2020. The results of our study provide detailed information for the local government on the TSS concentrations in the PAD.