Remote Sensing Retrieval of Cloud Top Height Using Neural Networks and Data from Cloud-Aerosol Lidar with Orthogonal Polarization.

In order to enhance the retrieval accuracy of cloud top height (CTH) from MODIS data, neural network models were employed based on Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) data. Three types of methods were established using MODIS inputs: cloud parameters, calibrated radiance, and a combination of both. From a statistical standpoint, models with combination inputs demonstrated the best performance, followed by models with calibrated radiance inputs, while models relying solely on calibrated radiance had poorer applicability. This work found that cloud top pressure (CTP) and cloud top temperature played a crucial role in CTH retrieval from MODIS data. However, within the same type of models, there were slight differences in the retrieved results, and these differences were not dependent on the quantity of input parameters. Therefore, the model with fewer inputs using cloud parameters and calibrated radiance was recommended and employed for individual case studies. This model produced results closest to the actual cloud top structure of the typhoon and exhibited similar cloud distribution patterns when compared with the Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) CTHs from a climatic statistical perspective. This suggests that the recommended model has good applicability and credibility in CTH retrieval from MODIS images. This work provides a method to improve accurate CTHs from MODIS data for better utilization.

Long-term effects of rewetting and drought on GPP in a temperate peatland based on satellite remote sensing data.

Rewetting previously drained peatlands restores the critical function of peatlands as long-term carbon storages and sinks currently threatened by climate change and additional human-induced disturbances. Understanding and projecting the restoration process by rewetting, however, currently face a pressing challenge, the lack of consistent and gap-free records of important carbon cycling indicators of peatlands such as the gross primary production (GPP) over long term. In this study, we reconstructed the GPP in a rewetted peatland called Zarnekow (Fluxnet-ID: DE-Zrk) in Germany from 2000 to 2020 by combining long-term satellite observations and limited-term tower-based eddy covariance (EC) measurements based on Random Forest regression models. The R2 between the reconstructed data and EC data was 0.6. The reasonable reconstruction of long-term GPP enabled trend analysis that identified two distinct periods of decreasing/increasing in GPP due to rewetting and droughts. Rewetting in the winter of 2004 and 2005 stabilized GPP after a decreasing period. A drought in 2018 significantly increased GPP, and GPP remained high over the following two years. Furthermore, the month-specific trends show significant seasonality at this site, specifically, an increasing trend over the 21 years in the growing-season months of June to August and a decreasing trend in the other months. The most important variables for satellite-based estimates of GPP at this site include total evapotranspiration, land surface temperature, enhanced vegetation index and near-infrared reflectance vegetation index. Long-term analyses of carbon fluxes through the combination of satellite observations and EC measurements provide crucial insights into the restoration of carbon sequestration functions in rewetted peatlands.

Development and application of a new sensitivity analysis model for the remote sensing retrieval of heavy metals in water.

This work proposes a new sensitivity analysis model, referred to as the D-δ(ε) model, for the remote sensing retrieval of heavy metals in bodies of water. By defining the reflectance ratio function (δ(ε)), we deduce the mathematical relationships between the heavy metal concentration sequences (Di) that can be effectively used for remote sensing retrievals and the radiometric resolution (ε) of the remote sensing instrument. Then, as a function of wavelength, we obtain the curve of the lower limit of the heavy metal concentrations in water that can be retrieved by remote sensing. To demonstrate the advantages of this model, we take two compounds, copper sulphate (CuSO4) and cadmium sulphide (CdS), as examples to discuss the remote sensing sensitivity of different wavelengths when retrievals are performed using the Chinese HJ-1A's hyperspectral imager (HSI). The results showed that the lowest detectable concentration of CuSO4 in the wavelength range of 460.04-496 nm (corresponding to bands 1-17 of the HSI image) can be below 0.15 mg/L, while the concentration of CdS can be lower than 0.001 mg/L in the separate ranges of 460.04-493.59 nm (bands 1-16) and 526.885-594.79 nm (bands 29-51). This model clearly demonstrates the mathematical relationship obeyed by "D-ε". Additionally, this model can not only calculate the retrieval concentration sequences at any observation wavelength but also intuitively provide the curve of the lower concentration limit for heavy metal retrievals. This work provides a theoretical basis for the selection of the most sensitive bands for remote sensing retrieval using hyperspectral images in the future.

Spatio-Temporal Characteristics of PM2.5 Concentrations in China Based on Multiple Sources of Data and LUR-GBM during 2016-2021.

Fine particulate matter (PM2.5) has a continuing impact on the environment, climate change and human health. In order to improve the accuracy of PM2.5 estimation and obtain a continuous spatial distribution of PM2.5 concentration, this paper proposes a LUR-GBM model based on land-use regression (LUR), the Kriging method and LightGBM (light gradient boosting machine). Firstly, this study modelled the spatial distribution of PM2.5 in the Chinese region by obtaining PM2.5 concentration data from monitoring stations in the Chinese study region and established a PM2.5 mass concentration estimation method based on the LUR-GBM model by combining data on land use type, meteorology, topography, vegetation index, population density, traffic and pollution sources. Secondly, the performance of the LUR-GBM model was evaluated by a ten-fold cross-validation method based on samples, stations and time. Finally, the results of the model proposed in this paper are compared with those of the back propagation neural network (BPNN), deep neural network (DNN), random forest (RF), XGBoost and LightGBM models. The results show that the prediction accuracy of the LUR-GBM model is better than other models, with the R2 of the model reaching 0.964 (spring), 0.91 (summer), 0.967 (autumn), 0.98 (winter) and 0.976 (average for 2016-2021) for each season and annual average, respectively. It can be seen that the LUR-GBM model has good applicability in simulating the spatial distribution of PM2.5 concentrations in China. The spatial distribution of PM2.5 concentrations in the Chinese region shows a clear characteristic of high in the east and low in the west, and the spatial distribution is strongly influenced by topographical factors. The seasonal variation in mean concentration values is marked by low summer and high winter values. The results of this study can provide a scientific basis for the prevention and control of regional PM2.5 pollution in China and can also provide new ideas for the acquisition of data on the spatial distribution of PM2.5 concentrations within cities.

[Remote Sensing Monitoring on Spatial Differentiation of Suspended Sediment Concentration in a River-Lake System Based on Sentinel-2 MSI Imaging:A Case for Shengjin Lake and Connected Yangtze River Section in Anhui Province].

Carrying out monitoring of suspended sediment concentration in river and lake systems is of great significance for understanding the laws of sediment transport in water and formulating policies on water environmental control. Taking Shengjin Lake and the connected Yangtze river section in Anhui province as the study area, band reflectance of a Sentinel-2 MSI sensor is simulated according to field spectral datasets, and the retrieval model is established by statistical regression from the synchronized suspended sediment concentration measurements. Then, the retrieved results from 28 scene MSI images during 2017-2019 are used to analyze the spatiotemporal variation of suspended sediment concentration in rivers and lakes, and the influence of water level variation on their spatial differentiation is also discussed. The results show that:① The retrieval model established by the ratio of the sixth band to the third band of the MSI sensor is suitable for high-turbidity water type, with high accuracy (R2=0.863, RMSE=22.211 mg·L-1). ② Spatially, the suspended sediment concentration near the lake entrances, northwestern parts of the upper and middle lake areas, and the lower lake is relatively higher, and that of Shengjin Lake is lower than that of the Yangtze River overall except for in summer. Temporally, the suspended sediment concentration in Shengjin Lake is relatively lower in summer and higher in other seasons, while the connected Yangtze River section exhibits the opposite intra-annual variation. ③ The water level, which is caused by the connectivity of rivers and lakes under the influence of the sluice, is the key factor affecting the spatial differentiation of suspended sediment concentration in the river and lake system. The suspended sediment concentration in Shengjin Lake contributes to the Yangtze River in dry and normal water periods, and that in the normal water period is more significant. In contrast, during the flood period, the correlation between suspended sediment concentration in the Yangtze River and that in Shengjin Lake is not obvious.