Monitoring water quality using proximal remote sensing technology.

Monitoring water quality using proximal remote sensing technology

A generalized machine learning approach for dissolved oxygen estimation at multiple spatiotemporal scales using remote sensing.

In order to use in situ sensed reflectance to monitor the concentrations of chlorophyll-a (Chl-a) and total suspended particulate (TSP) of waters in the Pearl River Delta, which is featured by the highly developed network of rivers, channels and ponds, 135 sets of simultaneously collected water samples and reflectance were used to test the performance of the traditional empirical models (band ratio, three bands) and the machine learning models of a back-propagation neural network (BPNN). The results of the laboratory analysis with the water samples show that the Chl-a ranges from 3 to 256 µg·L−1 with an average of 39 µg·L−1 while the TSP ranges from 8 to 162 mg·L−1 and averages 42.5 mg·L−1. Ninety sets of 135 samples are used as training data to develop the retrieval models, and the remaining ones are used to validate the models. The results show that the proposed band ratio models, the three-band combination models, and the corresponding BPNN models are generally successful in estimating the Chl-a and the TSP, and the mean relative error (MRE) can be lower than 30% and 25%, respectively. However, the BPNN models have no better performance than the traditional empirical models, e.g., in the estimation of TSP on the basis of the reflectance at 555 and 750 nm (R555 and R750, respectively), the model of BPNN (R555, R750) has an MRE of 23.91%, larger than that of the R750/R555 model. These results suggest that these traditional empirical models are usable in monitoring the optically active water quality parameters of Chl-a and TSP for eutrophic and turbid waters, while the machine learning models have no significant advantages, especially when the cost of training samples is considered. To improve the performance of machine learning models in future applications on the basis of ground sensor networks, large datasets covering various water situations and optimization of input variables of band configuration should be strengthened.

Evaluating traditional empirical models and BPNN models in monitoring the concentrations of chlorophyll-a and total suspended particulate of eutrophic and turbid waters

Remote sensing provides full-coverage and dynamic water quality monitoring with high efficiency and low consumption. Deep learning (DL) has been progressively used in water quality retrieval because it efficiently captures the potential relationship between target variables and imagery. In this study, the multimodal deep learning (MDL) models were developed and rigorously validated using atmospherically corrected Landsat remote sensing reflectance data and synchronous water quality measurements for estimating long-term Chlorophyll- a (Chl- a ), total phosphorus (TP), and total nitrogen (TN) in Lake Simcoe, Canada. Since TP and TN are non-optically active, their retrievals were based on the fact that they are closely related to the optically active constituents (OACs) such as Chl- a . We trained the MDL models with one in-situ measured data set (for Chl- a , N = 315, for TP and TN, N = 303), validated the models with two independent data sets ( N = 147), and compared the model performances with several DL, machine learning, and empirical algorithms. The results indicated that the MDL models adequately estimated Chl- a (mean absolute error (MAE) = 32.57%, Bias = 10.61%), TP (MAE = 42.58%, Bias = −2.82%), and TN (MAE = 35.05%, Bias = 13.66%), and outperformed several other candidate algorithms, namely the progressively decreasing deep neural network (DNN), a DNN with trainable parameters similar to MDL but without splitting input features, the eXtreme Gradient Boosting, the support vector regression, the NASA Ocean Color two-band and three-band ratio algorithms, and another empirical algorithm of Landsat data in clear lakes. Using the MDL models, we reconstructed the historical spatiotemporal patterns of Chl- a , TP, and TN in Lake Simcoe since 1984, and investigated the effects of two water quality improvement programs. In addition, the physical mechanism and interpretability of the MDL models were explored by quantifying the contribution of each feature to the model outputs. The framework proposed in this study provides a practical method for long-term Chl- a , TP, and TN estimation at the regional scale. 

Performance of deep learning in mapping water quality of Lake Simcoe with long-term Landsat archive

Water-quality monitoring for small urban waterbodies by remote sensing gets to be difficult due to the coarse spatial resolution of remote-sensing imagery. The recently launched Sentinel-2 produces...

A machine learning-based strategy for estimating non-optically active water quality parameters using Sentinel-2 imagery

Water quality retrieval for small urban waterbodies by remote sensing get used to be difficult due to coarse spatial resolution of the remote sensing imagery. The recently launched Sentinel-2 produces imagery with a spatial resolution of 10 m. It provides an opportunity to solve the problem of retrieving water quality for small waterbodies. Additionally, many water management issues also require fine resolution of imagery, e.g. illegal discharge to an urban waterbody. Since illegal discharges are an important issue for urban water management, chemical oxygen demand (COD), total phosphorous (TP), and total nitrogen (TN) were chosen as the target parameters for water quality retrieval in this study. COD, TP and TN, however, are non-optically active parameters. There were limited studies in the past to retrieve these parameters in comparison with optically active parameters, e.g. Chlorophyll-A etc. This study compared three machine learning models, namely Random Forest (RF), Support Vector Regression (SVR), and Neural Networks (NN), to investigate the opportunity to retrieve the above non-optically active parameters. Results showed that R2 of TP, TN, and COD by NN, RF and SVR were 0.94, 0.88, and 0.86, respectively. The performances of water quality retrieval for these non-optically active parameters were significantly improved by the optimized machine learning models. These models hence solved the problem to use remote sensing data to retrieve these non-optically active water quality parameters and provided a new monitoring strategy for small waterbodies. Water quality mapping obtained by Sentinel-2 imagery provided a full spatial coverage of the water quality characterization for the entire water surface. Compared with water samples collecting and testing, it greatly reduced labor cost, reagents cost, and waste treatment cost. It also may help identify illegal discharges to urban waterbodies. The method developed in this research provides a new practical and efficient water quality monitoring strategy in managing water with consideration of environmental sustainability.

/pdf/retrieval-of-non-optically-active-parameters-for-small-scale-1xdtzxv0rj.pdf

Xiaolong Guo

Papers

A machine learning-based strategy for estimating non-optically active water quality parameters using Sentinel-2 imagery

Retrieval of Non-Optically Active Parameters for Small Scale Urban Waterbodies by a Machine Learning-Based Strategy