We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
A data-driven approach for the assessment of the thermal stratification of reservoirs based on readily available data
Summary
Researchers used a data-driven machine learning approach to assess the thermal structural integrity of materials under variable conditions, providing predictive models that can reduce reliance on costly physical testing. The methodology has broader applications for materials used in environments with high thermal stress.
A data-driven approach to assess the occurrence of thermal stratification and the depth of the thermocline in water masses has been developed and tested in the Spanish reservoir of El Val. The novelty of this approach is that it relies only on readily available data that can be collected for almost any reservoir, providing water managers with a transferable tool that can be easily adapted for any other reservoirs or lakes. The input variables were meteorological data, the water level and the output flow. A non-supervised clustering technique, k-means, was used to identify the stratification period with unlabelled data, that is to say inferring patterns when data from the target variable is not available. As a supervised method, Artificial Neural Networks were used to classify a given day as having or not having stratification and, in the positive case, to infer the depth of the thermocline. The classification showed a very high accuracy (96%) and the estimation of the thermocline depth showed a mean absolute error (MAE) of 1.94 m and 1.99 m in the training and test fractions, respectively. Shapley Additive Explanations (SHAP) values were used to improve the explainability and they revealed that the most important features to infer the depth of the thermocline were the water level, the daily average solar irradiance and the air temperature.
Sign in to start a discussion.
More Papers Like This
Drinking water potability prediction using machine learning approaches: a case study of Indian rivers
Researchers applied machine learning techniques to predict drinking water quality in Indian rivers based on key parameters like pH, dissolved oxygen, and bacterial counts. Their models achieved high accuracy in classifying water as potable or non-potable. The study demonstrates how data-driven approaches could help developing countries monitor water safety more efficiently, especially in regions where traditional testing infrastructure is limited.
Materials Informatics for Mechanical Deformation: A Review of Applications and Challenges
This review covers machine learning methods applied to predicting and understanding mechanical properties of materials from large datasets. It is an engineering informatics paper and is not related to microplastics or environmental health.
Thermo‐based fatigue life prediction: A review
Not relevant to microplastics — this review covers thermography-based methods for predicting the fatigue life of metals under cyclic stress, with no connection to plastic pollution or environmental health.
Water Quality Monitoring And Ground Water Level Prediction Using Machine Learning
Researchers applied machine learning techniques to water quality monitoring and groundwater level prediction, demonstrating the potential of data-driven approaches for environmental sensing and resource management.
Using machine learning and a data-driven approach to identify the small fatigue crack driving force in polycrystalline materials
Researchers used machine learning and Bayesian network analysis on 4D microscopy data from cracking metal samples to identify which microstructural features best predict how small fatigue cracks grow and in which direction. The resulting analytical model outperformed existing fatigue metrics, offering a more accurate tool for predicting when and how structural metal components will fail under repeated stress.