Combining Artificial Neural Networks with Causal Inference for Total Phosphorus Concentration Estimation and Sensitive Spectral Bands Exploration Using MODIS

Abstract

The total phosphorus (TP) concentration is a key water quality parameter for water monitoring and a major indicator of the state of eutrophication in inland lakes. Using remote-sensing to estimate TP concentration is useful, as it provides a synoptic view of the entire water region; however, the weak optical characteristics of TP lead to difficulty in accurately estimating TP concentration. The differences in water characteristics and components between lakes mean that most TP estimation methods are not applicable to all lakes. An artificial neural network (ANN) model was created to represent the correlation between TP concentration and the spectral bands of Moderate Resolution Imaging Spectroradiometer (MODIS) images in different research areas. We investigated the causal inference under the potential outcome framework to analyze the sensitivity of each band with regard to the TP concentration of different lakes for the research of water characteristics. Our results show that the accuracy of the ANN-based TP concentration estimation, with R2 > 0.73, root mean squared error (RMSE) < 0.037 mg/L in Lake Okeechobee and R2 > 0.73, RMSE < 4.1 μg/L in Lake Erie, respectively, is much higher than traditional empirical methods, e.g., linear regression. We found that the sensitive bands of TP concentration in Lake Erie are blue bands, whereas the sensitive bands in Lake Okeechobee are green bands. Various TP concentration maps were drawn to indicate the distribution of TP concentration and its tendency to change. The maps show that the distribution of TP concentration closely corresponds to the shore land-use, and a high TP concentration corresponds to the latest algal blooms breakout. Our proposed approach shows good potential for the remote-sensing estimation of TP concentration for inland lakes. Identifying the sensitive bands not only help characterize the lakes, but will also help the researchers to further observe the TP concentration of specific lakes in an efficient way.

Changes in Nutrient Concentrations in Shenzhen Bay Detected Using Landsat Imagery between 1988 and 2020

“…Sinshaw et al established a retrieval model for summertime C TN and C TP with pH, electrical conductivity, and turbidity as the input parameters for an NN and found that the pH had the highest sensitivity [16]. The above research shows the feasibility of sensing technology for nutrient-concentration retrieval, and it also reflects the advantages of ML methods for such retrieval in coastal waters [13][14][15][16].…”

“…Liu et al established a retrieval model for C TP using an SVM model, which yielded a retrieval accuracy (R 2 ) of 0.604 [13]. Ding et al estimated C TP with an artificial neural network and achieved a retrieval accuracy (R 2 ) greater than 0.73 [14]. Jiang et al found that the extra-trees regression algorithm was the most suitable for the inversion of C TN in the Miyun Reservoir and yielded an absolute square error of 0.000065 [15].…”

Retrieval of Total Phosphorus Concentration in the Surface Water of Miyun Reservoir Based on Remote Sensing Data and Machine Learning Algorithms

“…As a source of high-quality water, reservoirs generally have better water quality than rivers and thus have become important drinking water sources in many regions of China [23,24]. Therefore, water quality and the pollution monitoring of reservoir areas have received great attention from scholars at home and abroad for a long time [25].…”