The Weighted Values of Solar Evaporation’s Environment Factors Obtained by Machine Learning

Abstract

Enhancing the efficiency of solar still is important for solar stills. In this study, the weighted values of environment factors (descriptors) on the efficiency of solar evaporation are obtained by using a machine learning algorithm, random forest. To verify the advancement between random forest and mathematical data analysis, two traditional methods, pair wise plots and Pearson correlation analysis, are conducted for comparison. Experimental data are obtained from around 100 articles since 2014. The results indicated that traditional methods failed at obtaining reasonable weighted values, while random forest is competent. It is found that thermal design is the most significant descriptors to obtain a high efficiency. The lack of complete dataset is the main challenge for more in-depth and comprehensive analysis. This work may promote the enhancement of production and efficiency of solar stills.

Optimizing E-commerce Inventory to prevent Stock Outs using the Random Forest Algorithm Approach

“…RF has demonstrated high accuracy and mean area under the curve (AUC) scores in predicting and sizing vaults for myopia correction [38]. Additionally, RF has been found to outperform traditional methods in obtaining reasonable weighted values for solar evaporation's environmental factors, indicating its competence over traditional methods [39]. Furthermore, RF has been applied to predict Listeria spp.…”

An anthracene-based hydrogen-bonded organic framework as a bifunctional fluorescent sensor for the detection of γ-aminobutyric acid and nitrofurazone

“…Deep ML also enforces ANN intelligence through extensive data training, while previous studies rarely involved the combination of fluorescence sensing and deep ML. [69][70][71][72][73][74][75][76][77][78] Hence, the invention of artificial Intelligence systems (AIS) based on the fluorescence sensing technology by deep ML will be a great challenge. Here, we reported a case of HOF-DBA assembled by 4,4′-(anthracene-9,10-diyl)dibenzoic acid (H 2 DBA) via hydrogen bonding and intermolecular forces.…”

Fractional description for the rate‐dependent viscoelastic response of tough hydrogels

“…[17][18][19][20] Whereas the direct summation of elastic free-energy and viscoelastic/hyperelastic ones is not suitable for the soft anomalous materials, specifically tough and synthetic hydrogels, due to their intrinsic mechanical properties of mixed elasticity and viscosity. 21 The approach of machine learning (ML) is developed to allow a machine to train and study from samples, and has been applied in several application areas including manufacturing, 22 composite materials design, 23,24 et al However, the ML weightily depends on the quality of data and algorithm, which is also prone to exist the problem of overfitting and correlation. Meanwhile, the analytical model cannot be obtained.…”