Search

In wastewater treatment plants (WWTPs), the stochastic nature of influent wastewater and operational and weather conditions cause fluctuations in effluent quality. Data-driven models can forecast effluent quality a few hours ahead as a response to the influent characteristics, providing enough time to adjust system operations and avoid undesired consequences. However, existing data for training models are often incomplete and contain missing values. On the other hand, collecting additional data by installing new sensors is costly. The trade-off between using existing incomplete data and collecting costly new data results in three data challenges faced when developing data-driven WWTP effluent forecasters. These challenges are to determine important variables to be measured, the minimum number of required data instances, and the maximum percentage of tolerable missing values that do not impede the development of an accurate model. As these issues are not discussed in previous studies, in this research, for the first time, a comprehensive analysis is done to provide answers to these challenges. Another issue that arises in all data-driven modeling is how to select an appropriate forecasting model. This paper addresses these issues by first testing nine machine learning models on data collected from three wastewater treatment plants located in Iran, Australia, and Spain. The most accurate forecaster, Bayesian network, was then used to address the articulated challenges. Key variables in forecasting effluent characteristics were flow rate, total suspended solids, electrical conductivity, phosphorus compounds, wastewater temperature, and air temperature. A minimum of 250 samples was needed during the model training to achieve a great reduction in the forecasting error. Moreover, a steep increase in the error was observed should the portion of missing values exceed 10%. The results assist plant managers in estimating the necessary data collection effort to obtain an accurate forecaster, contributing to the quality of the effluent. [Display omitted] • Bayesian network is benchmarked against eight AI models to predict wastewater quality. • Bayesian networks can handle missing value in input data due to probabilistic nature. • Key variables in WWTP quality and quantity were specified. • Input data quality has a huge role in successful development of data-driven models. • The prediction error sharply increases when the portion of missing data exceeds 10%. [ABSTRACT FROM AUTHOR]

Incidences of disease, dieback, decline or mortality, some of which induced or enhanced by climate change, threaten the sustainability of forest stands in many ecosystems. Spatially explicit prediction of disease onset remains challenging, however, due to the involvement of several causative agents. In this paper, we developed a generic framework based on machine-learning algorithms and spatial analyses for landscape-level prediction of oak disease outbreaks caused by the charcoal fungus Biscogniauxia mediterranea in a mixed-oak forest of Mediterranean climate. For prediction, we used a set of fifteen causative factors as a cross-function of soil, site and stand-related predictors. A total of 80 sample plots, including 1134 affected trees, were surveyed and used for the modeling process at the 5600-ha landscape level of the southern Zagros, Iran, where the disease occurs in roughly 25% of forest lands. Ten machine learning algorithms were explored and the performance of each algorithm to predict oak disease outbreak was evaluated. The modeling framework used maximum entropy to remove the least influential variables and build the status-quo management scenario to which the results of the prediction models were compared. Results showed that the random forests algorithm (AUC = 0.96: Precision = 0.71: Accuracy = 0.90: F-Measure = 0.70) achieved significantly better results than the status-quo management (Precision = 0.13: Accuracy = 0.67: F-Measure = 0.12) and any other algorithm. Soil chemical properties (NPK, organic carbon and EC) and landform predictors (slope, distance to roads, and TWI) were major forecasters of oak disease outbreak identified by the random forest algorithm. Geostatistical analysis enabled the creation of a map that identified sites at higher risk of infestation, allowing epidemiologists and forest managers to find sites likely to be infested. Consequently, financial resources can be allocated and management practices such as sanitation felling treatments applied across large forest landscapes to minimize the risk of spread and severity to uninfested high-value trees on nearby or adjacent land zones that are in the early stage of epidemics. • Soil and landform attributes explain short-term presence of oak charcoal disease. • Random forest (RF) algorithms outperform nine other machine learning algorithms. • RF predicts 41% of Brant's oak at moderate disease intensity in southern Zagros. • RF algorithm predicts oak dieback, decline or mortality with 96% accuracy. • Machine-learning algorithms predict spatial charcoal disease intensity in Brant's oak. [ABSTRACT FROM AUTHOR]

Due to land-use and hydrology changes, people are constantly exposed to floods. The adverse impact of floods is greater on vulnerable populations that disproportionately inhabit flood-prone areas. This paper reports a comprehensive study on flood vulnerability of flood prone areas in residential areas of the Tajan watershed, Iran in two periods before 2006 and after 2006. Flood prone area were determined by the random forest (RF) and K-nearest neighbor (KNN) machine learning methods. To reduce time and cost, the vulnerability was assessed only in areas with very high flood hazard using 4 main criteria (social, policy, economic, infrastructure), 40 items, and 210 questionnaires across 40 villages. Independent t -test, Kruskal-Wallis, and paired t -test were used for statistical analysis of questionnaire data. The results of machine learning models (MLMs) showed that the RF model with AUC = 0.92% is more accurate in determining flood prone areas. The results of paired t -test showed that the three criteria of social (mean P1 = 2.97 and P2 = 3.35), infrastructure (mean P1 = 2.88 and P2 = 3.25), and policy (mean P1 = 3.02 and P2 = 3.50) had significant changes in both periods. The Kruskal-Wallis test also revealed the mean of all four criteria in both periods and all sub-watersheds, except three sub-watersheds 10 (Khalkhil village), 19 (Tellarem and Kerasp villages), and 23 (Dinehsar and Jafarabad), had a significant difference. The results of the t -test also showed a decrease in vulnerability in the second period (before 2006) compared to the first period (after 2006), so the number of sub-watersheds in the very high vulnerability class was more in the first period than in the second period. A vulnerability map was developed using three factors of risk zone area, area of each sub-watershed, and population of each sub-watershed. • Using machine learning methods and field survey to assess vulnerability in flood hazard areas. • Investigating temporal and spatial variability in flood vulnerability of Tajan watershed. • Prioritizing flood-vulnerable areas using related criteria and indicators. [ABSTRACT FROM AUTHOR]