Random forest-based modeling of stream nutrients at national level in a data-scarce region

A novel approach to identify priority areas for optimal nutrient management in mixed land-use watersheds through nutrient budget assessment

Excessive nutrient supply in agricultural regions has led to various environmental issues, thereby requiring concentrated management owing to its persistent upward trend. Nutrient budgets (NBs), a vital agricultural environmental indicator, are employed for nutrient management in agricultural areas, using data surveyed by administrative agencies. However, the spatial extent of nutrient data for nutrient budgeting is limited by administrative boundaries according to the surveying organization, posing challenges in interpreting spatial patterns at the watershed level. In this study, a novel approach was developed to identify priority nutrient management areas by applying hot spot spatial analysis to watershed-level NBs, considering hydrological characteristics. This method was applied to approximately 850 subwatersheds across the Republic of Korea, where land cover characteristics are complex. Reassessing nutrient budgets at the watershed scale, accounting for overlapping administrative boundary areas and crop cultivation ratios, indicated similar levels between the two methods. Hot spot analysis revealed that watersheds with elevated NBs mirrored the spatial patterns of livestock excreta and cropland. The spatial distribution characteristics of watersheds with high nutrient levels in rivers corresponded with the concentration characteristics of industrial and commercial areas. Therefore, applying watershed-level NBs based on land cover ratios that consider nutrient input characteristics in agricultural regions is deemed appropriate for selecting priority nutrient management areas. Collectively, this study presents a method for selecting nutrient management priority areas by simultaneously considering the spatial characteristics of various environmental factors, such as land cover, livestock excreta, river water quality, and land area-based watershed-specific NBs. The proposed approach, considering mixed land cover characteristics, is anticipated to be valuable for selecting priority management areas in watersheds with diverse pollution sources. Future research is needed to explore nutrient budgets within watersheds, the influence of land use on pollution sources, and their correlation with water quality.

A random forest approach to improve estimates of tributary nutrient loading

Estimating constituent loads from discrete water quality samples coupled with stream discharge measurements is critical for management of freshwater resources. Nutrient loads calculated based on discharge-concentration relationships form the basis of government nutrient load targets and scientific studies of the response of receiving waters to external loads. In this study, a new model is developed using random forests and applied to estimate concentrations and loads of total phosphorus, dissolved phosphorus, total nitrogen, and chloride, using data from 17 tributaries to Lake Champlain monitored from 1992 to 2021. I benchmark this model against one of the most widespread models currently used to estimate nutrient loads, Weighted Regressions on Time, Discharge, and Season (WRTDS). The random forest model outperformed both the base WRTDS model and an extension of the WRTDS model using Kalman filtering in the great majority of cases, likely due to the inclusion of rate-of-change in discharge and antecedent discharge over different leading windows as predictors, and to the flexibility of the random forest to model predictor-response relationships. The random forest also had useful visualization capabilities which provided important process insights. WRTDS remains a useful model for many applications, but this study represents a promising new approach for load estimation which can be applied easily to existing datasets, and which is easy to customize for different applications.

Estimating the temporal and spatial distribution and threats of bisphenol A in temperate lakes using machine learning models

Bisphenol A (BPA) is easily enriched in many human-disturbed watersheds, particularly lakes with poor water mobility, which is posing a threat to aquatic biota. While previous studies have focused on the concentration of BPA in water and its toxicity to aquatic organisms, a small amount of measured data is not enough to reveal the temporal and spatial distribution and threats of BPA, and estimate the ecological risk in watersheds. Therefore, we collected 164 measured BPA data points from Taihu Lake to develop machine learning models using random forest (RF), support vector machine (SVM) and least square regression (LSR) and created month-by-month watershed prediction maps in temperate lakes to estimate the spatiotemporal distribution and threats of BPA. Due to RF's superior robustness to noisy data, the RF model exhibits the best performance among the three algorithms. The RF model showed acceptable predictive performance on the modeling dataset (coefficients of determination and root-mean-square error for the training set were 0.927 and 17.499, respectively, and 0.607, 39.645 for the validation set, respectively). The maps indicated that areas susceptible to anthropogenic activities were more severely polluted by BPA, and rainy climate may favor the migration of BPA to aquatic ecosystems. The model was also applied to predict 42 data points of BPA collected from Dianchi Lake, and the results showed that most predicted data were within a factor of 10 of the measured data, but the prediction accuracy of the model has declined. The ecological risks in the two lakes were evaluated and attention should be paid to the regions with higher risks. Our study provided a novel idea for comprehensive monitoring of an unconventional trace pollutant with endocrine disrupting effects in aquatic ecosystems and analyzing their spatiotemporal distribution, which will contribute to the scientific assessment of the ecological risk of BPA.

Forecasting water quality variable using deep learning and weighted averaging ensemble models

Water quality variables, including chlorophyll-a (Chl-a), play a pivotal role in comprehending and evaluating the condition of aquatic ecosystems. Chl-a, a pigment present in diverse aquatic organisms, notably algae and cyanobacteria, serves as a valuable indicator of water quality. Thus, the objectives of this study encompass: (1) the assessment of the predictive capabilities of four deep learning (DL) models - namely, recurrent neural network (RNN), long short-term memory (LSTM), gated recurrence unit (GRU), and temporal convolutional network (TCN) - in forecasting Chl-a concentrations; (2) the incorporation of these DL models into ensemble models (EMs) employing genetic algorithm (GA) and non-dominated sorting genetic algorithm (NSGA-II) to harness the strengths of each standalone model; and (3) the evaluation of the efficacy of the developed EMs. Utilizing data collected at 15-min intervals from Small Prespa Lake (SPL) in Greece, the models employed hourly Chl-a concentration lag times, extending up to 6 h, as models' inputs to forecast Chla (t+1). The proposed models underwent training on 70% of the dataset and were subsequently validated on the remaining 30%. Among the standalone DL models, the GRU model exhibited superior performance in Chl-a forecasting, surpassing the RNN, LSTM, and TCN models by 8%, 2%, and 2%, respectively. Furthermore, the integration of DL models through single-objective GA and multi-objective NSGA-II optimization algorithms yielded hybrid models adept at effectively forecasting both low and high Chl-a concentrations. The ensemble model based on NSGA-II outperformed standalone DL models as well as the GA-based model across a range of evaluation indices. For instance, considering the R-squared metric, the study's findings demonstrated that the EM-NSGA-II stands out with exceptional effectiveness compared to DL and EM-GA models, showcasing improvements of 14% (RNN), 8% (LSTM), 6% (GRU), 8% (TCN), and 3% (EM-GA) during the testing phase.

Global patterns and key drivers of stream nitrogen concentration: A machine learning approach

Anthropogenic loading of nitrogen to river systems can pose serious health hazards and create critical environmental threats. Quantification of the magnitude and impact of freshwater nitrogen requires identifying key controls of nitrogen dynamics and analyzing both the past and present patterns of nitrogen flows. To tackle this challenge, we adopted a machine learning (ML) approach and built an ML-driven representation that captures spatiotemporal variability in nitrogen concentrations at global scale. Our model uses random forests to regress a large sample of monthly measured stream nitrogen concentrations onto a set of 17 predictors with a spatial resolution of 0.5-degree over the 1990-2013, including observations within the pixel and upstream drivers. The model was validated with data from rivers outside the training dataset and was used to predict nitrogen concentrations in 520 major river basins of the world, including many with scarce or no observations. We predicted that the regions with highest median nitrogen concentrations in their rivers (in 2013) were: United States (Mississippi), Pakistan, Bangladesh, India (Indus, Ganges), China (Yellow, Yangtze, Yongding, Huai), and most of Europe (Rhine, Danube, Vistula, Thames, Trent, Severn). Other major hotspots were the river basins of the Sebou (Morroco), Nakdong (South Korea), Kitakami (Japan), and Egypt's Nile Delta. Our analysis showed that the rate of increase in nitrogen concentration between 1990s and 2000s was greatest in rivers located in eastern China, eastern and central parts of Canada, Baltic states, Pakistan, mainland southeast Asia, and south-eastern Australia. Using a new grouped variable importance measure, we also found that temporality (month of the year and cumulative month count) is the most influential predictor, followed by factors representing hydroclimatic conditions, diffuse nutrient emissions from agriculture, and topographic features. Our model can be further applied to assess strategies designed to reduce nitrogen pollution in freshwater bodies at large spatial scales.

Large-scale prediction of stream water quality using an interpretable deep learning approach

Deep learning methods, which have strong capabilities for mapping highly nonlinear relationships with acceptable calculation speed, have been increasingly applied for water quality prediction in recent studies. However, it is argued that the practicality of deep learning methods is limited due to the lack of physical mechanics to explain the prediction results of water quality changes. A knowledge gap exists in rationalizing the deep learning results for water quality predictions. To address this gap, an interpretable deep learning framework was established to predict the spatiotemporal variations of water quality parameters in a large spatial region. Mereological, land-use, and socioeconomic variables were adopted to predict the daily variations of stream water quality parameters across 138 sub-catchments in a total of over 575,250 km² in southern China. The coefficients of determination of chemical oxygen demand (COD), total phosphorus (TP), and total nitrogen (TN) predictions were over 0.80, suggesting a satisfactory prediction performance. The model performance in terms of prediction accuracy could be improved by involving land-use and socioeconomic predictors in addition to hydrological variables. The SHapley Additive exPlanations method used in this study was demonstrated to be effective for interpreting the prediction results by identifying the significant variables and reasoning their influencing directions on the variation of each water quality parameter. The air temperature, proportion of forest area, grain production, population density, and proportion of urban area in each sub-catchment as well as the accumulated rainfall within the previous 3 days were identified as the most significant variables affecting the variations of dissolved oxygen, COD, ammoniacal nitrogen(NH₃-N), TN, TP, and turbidity in the stream water in the case area, respectively.