Remote sensing (RS) water depth inversion is an important technology and the method of water depth measurement. Taking the waters around the islands outside the Pearl River Estuary as an example, five optical RS depth inversion algorithms were introduced. Then, five water depth inversion models were trained through the HJ-1B satellite RS image and the measured water depth data. The results show that the mean absolute error (MAE) of the deep learning model was the smallest (2.350 m), and that the distribution of predicted water depth points was closest to the actual value. Deep learning has been widely used in RS image classification and recognition and shows its advantages. Therefore, the deep learning model was applied to extract the depth of the shallow water. Meanwhile, the obtained inversion effect map is closest to the actual contour map. The water depth inversion performance of back propagation neural network model is better than that of the radial basis function (RBF) neural network model. Besides, the inversion accuracy of the RBF neural network may be affected due to the small amount of data and the improper number of hidden neurons. The results show broad application prospects of machine learning algorithms in RS water depth inversion. Also, this study provided data support for model optimization, training, and parameter setting.
7 August 2018 in IOP Conference Series: Materials Science and Engineering
Groundwater is an important fresh water resource, which is very important for human survival. In this study, the hydrogeological information of the study area was obtained through field investigation and data reference, and the groundwater flow field in the study area was constructed using GMS (Groundwater Modeling Systems) software. The actual drilling water level data was used for verification. Based on the groundwater flow field, combined with pollution source sampling and testing data, a groundwater pollutant transport model was constructed, and the pollution situation was comprehensively evaluated. The results showed that once the landfill leachate and lead-acid battery plant waste liquid leaked in the study area, the groundwater in more than 40% of the study area will be greatly affected and it was not easy to recover. Therefore, predicting and simulating the transport of groundwater pollutants has a certain value, and can provide a scientific basis for preventing and controlling environmental degradation and protecting groundwater resources.
17 July 2018 in IOP Conference Series: Earth and Environmental Science
The traditional assessment of risk of gas disaster in mine rely on experience of experts to determine weights. And human factors frequently lead to greater errors. In order to overcome these shortcomings, we used Monte Carlo method to improve analytic hierarchy process (AHP) method. We used a large number of random number simulation to replace experts judgment. It can avoid the interference of human factors. The new weights were used to assess the risk of gas disaster, and the fuzziness of traditional fuzzy comprehensive evaluation was eliminated. We used Monte Carlo-AHP Method to assess the risk of gas disaster in Gaoping mine in Shanxi Province, China, and got score of assessment of risk of gas disaster in the study area. The results show that assessment method based on Monte Carlo-AHP has better correlation and lesser error than traditional assessment method.