Genetic-Algorithm-Optimized Sequential Model for Water Temperature Prediction

Abstract

<jats:p>Advances in establishing real-time river water quality monitoring networks combined with novel artificial intelligence techniques for more accurate forecasting is at the forefront of urban water management. The preservation and improvement of the quality of our impaired urban streams are at the core of the global challenge of ensuring water sustainability. This work adopted a genetic-algorithm (GA)-optimized long short-term memory (LSTM) technique to predict river water temperature (WT) as a key indicator of the health state of the aquatic habitat, where its modeling is crucial for effective urban water quality management. To our knowledge, this is the first attempt to adopt a GA-LSTM to predict the WT in urban rivers. In recent research trends, large volumes of real-time water quality data, including water temperature, conductivity, pH, and turbidity, are constantly being collected. Specifically, in the field of water quality management, this provides countless opportunities for understanding water quality impairment and forecasting, and to develop models for aquatic habitat assessment purposes. The main objective of this research was to develop a reliable and simple urban river water temperature forecasting tool using advanced machine learning methods that can be used in conjunction with a real-time network of water quality monitoring stations for proactive water quality management. We proposed a hybrid time series regression model for WT forecasting. This hybrid approach was applied to solve problems regarding the time window size and architectural factors (number of units) of the LSTM network. We have chosen an hourly water temperature record collected over 5 years as the input. Furthermore, to check its robustness, a recurrent neural network (RNN) was also tested as a benchmark model and the performances were compared. The experimental results revealed that the hybrid model of the GA-LSTM network outperformed the RNN and the basic problem of determining the optimal time window and number of units of the memory cell was solved. This research concluded that the GA-LSTM can be used as an advanced deep learning technique for time series analysis.</jats:p>

A Methodology for Forecasting Dissolved Oxygen in Urban Streams

“…This preprosessing approach can be used for other water quality parameters such as temperature, which exhibit similar periodicity and trends and applied to other models. For example, a novel genetic algorithm (GA)-optimized long short-term memory (LSTM) water temperature model developed by Stajkowski et al [4] can be combined with this technique to increase accuracy. The main goal of developing accurate models of key water quality parameters is the forecasting and assessment of the impact of disturbances (anthropogenic, such as pollution, or climatic such as climate change) on aquatic habitat suitability and, therefore, the health of aquatic species.…”

“…Several studies have described the importance of both the diurnal and seasonal fluctuations of DO as it relates to fish habitats [3][4][5]. The occurrence of low DO concentrations, in a normally well-oxygenated river system, can cause mortality in fish and other aquatic life.…”

Vorhersage der Fließgewässertemperaturen in österreichischen Einzugsgebieten mittels Machine Learning-Verfahren

“…In der vorliegenden Studie wurden die beiden meistverbreiteten RNNs getestet, zum einen das Long short-term memory (LSTM)-Modell (Hochreiter und Schmidhuber 1997) und zum anderen das Gated recurrent unit (GRU)-Modell (Cho et al 2014). Den Autoren ist erst eine Studie bekannt, in der ein LSTM in Kombination mit einer Hyperparameteroptimierung verwendet wurde, um die stündliche Wassertemperatur in urbanen Flüssen vorherzusagen (Stajkowski et al 2020). Generell wurden LSTMs in letzter Zeit in einer Vielfalt an hydrologischen Studien verwendet und zeigten vielversprechende Resultate für Aufgaben in der Prognose von Zeitreihen (z.…”

Modeling the Relationship between Rice Yield and Climate Variables Using Statistical and Machine Learning Techniques

“…e performance of each model was assessed in terms of the mean squared error (MSE), correlation coefficient (R), mean absolute percentage error (MAPE), root mean squared error ratio (RSR) [32], BIAS value [33], and the Nash number.…”