Predicting groundwater availability is important to water sustainability and drought mitigation. Machine-learning tools have the potential to improve groundwater prediction, thus enabling resource planners to: (1) anticipate water quality in unsampled areas or depth zones; (2) design targeted monitoring programs; (3) inform groundwater protection strategies; and (4) evaluate the sustainability of groundwater sources of drinking water. This paper proposes a machine-learning approach to groundwater prediction with the following characteristics: (i) the use of a regression-based approach to predict full groundwater images based on sequences of monthly groundwater maps; (ii) strategic automatic feature selection (both local and global features) using extreme gradient boosting; and (iii) the use of a multiplicity of machine-learning techniques (extreme gradient boosting, multivariate linear regression, random forests, multilayer perceptron and support vector regression). Of these techniques, support vector regression consistently performed best in terms of minimizing root mean square error and mean absolute error. Furthermore, including a global feature obtained from a Gaussian Mixture Model produced models with lower error than the best which could be obtained with local geographical features.

Spectroscopy data are useful for modelling biological systems such as predicting quality parameters of horticultural products. However, using the wide spectrum of wavelengths is not practical in a production setting. Such data are of high dimensional nature and they tend to result in complex models that are not easily understood. Furthermore, collinearity between different wavelengths dictates that some of the data variables are redundant and may even contribute noise. The use of variable selection methods is one efficient way to obtain an optimal model, andthis was the aim of this work. Taking advantage of a non-contact spectrometer, near infrared spectral data in the range of 800–2500 nm were used to classify bruise damage in three apple cultivars, namely ‘Golden Delicious’, ‘Granny Smith’ and ‘Royal Gala’. Six prominent machine learning classification algorithms were employed, and two variable selection methods were used to determine the most relevant wavelengths for the problem of distinguishing between bruised and non-bruised fruit. The selected wavelengths clustered around 900 nm, 1300 nm, 1500 nm and 1900 nm. The best results were achieved using linear regression and support vector machine based on up to 40 wavelengths: these methods reached precision values in the range of 0.79–0.86, which were all comparable (within error bars) to a classifier based on the entire range of frequencies. The results also provided an open-source based framework that is useful towards the development of multi-spectral applications such as rapid grading of apples based on mechanical damage, and it can also be emulated and applied for other types of defects on fresh produce.

Rooibos is brewed from the medicinal plant Aspalathus linearis. It has a well-established wide spectrum of bio-activity properties, which in part may be attributed to the phenolic antioxidant power. The antioxidant capacity (AOC) of rooibos is related to its total phenolic content (TPC). The relation between TPC and AOC of randomly selected 51 fermented (FR) and 47 unfermented (UFR) rooibos samples was studied after extraction using water and methanol separately. The resulted extracts were assessed using two antioxidant assays, trolox equivalent antioxidant capacity (TEAC) and ferric reducing antioxidant power (FRAP). The results were analyzed using both simple statistical methods and machine learning. The analysis showed different trends of TPC and AOC correlations of FR and UFR samples, depending on the solvent used for extraction. The results of the water extracts showed similar TPC and higher AOC of FR than UFR samples, while the methanolic extracted samples showed higher TPC and AOC of UFR than FR. As a result, the methanolic extracts showed better agreement between TPC and AOC than water extracts. Possible explanations are given for these observed results. Although, the current literature demonstrates direct correlations of the TPC and AOC of rooibos water extracts. This study showed deviation and highlighted the importance of solvent selection and analysis methodology as an important factor in determining the TPC/AOC correlation and subsequently the expectation of the actual health benefits of rooibos herbal tea. In particular, unfermented and fermented samples can be accurately identified on the basis of a combination of assays (any two of TPC, FRAP and TEAC), especially if methanol is the solvent used. Machine learning analysis of assay data provides nearly identical results with classical statistical analytical methods. This is the first report on machine learning analysis and comparison of the TPC and AOC of rooibos herbal tea extracted with methanol and water, and highlights the importance of using methanol as a solvent to evaluate its AOC.

Machine learning (ML) has been utilized to predict climatic parameters, and many successes have been reported in the literature. In this paper, we scrutinize the effectiveness of five widely used ML algorithms in the monthly prediction of seasonal climatic parameters using monthly image data. Specifically, we quantify the predictive performance of these algorithms applied to five climatic parameters using various combinations of features. We compare the predictive accuracy of the resulting trained ML models to that of basic statistical estimators that are computed directly from the training data. Our results show that ML never significantly outperforms the statistical baseline, and underperforms for most feature sets. Unlike previous similar studies, we provide error bars for the relative performance of different predictors based on jackknife estimates applied to differences in predictive error magnitudes. We also show that the practice of shuffling data sequences which was employed in some previous references leads to data leakage, resulting in over-estimated performance. Ultimately, the paper demonstrates the importance of using well-grounded statistical techniques when producing and analyzing the results of ML predictive models.

Radio synchrotron emission originates from both massive star formation and black hole accretion, two processes that drive galaxy evolution. Efficient classification of sources dominated by either process is therefore essential for fully exploiting deep, wide-field extragalactic radio continuum surveys. In this study, we implement, optimize, and compare five widely used supervised machine-learning (ML) algorithms to classify radio sources detected in the MeerKAT International GHz Tiered Extragalactic Exploration (MIGHTEE)-COSMOS survey as star-forming galaxies (SFGs) and active galactic nuclei (AGNs). Training and test sets are constructed from conventionally classified MIGHTEE-COSMOS sources, and 18 physical parameters of the MIGHTEE-detected sources are evaluated as input features. As anticipated, our feature analyses rank the five parameters used in conventional classification as the most effective: the infrared–radio correlation parameter ($q_\mathrm{IR}$), the optical compactness morphology parameter (class_star), stellar mass, and two combined mid-infrared colours. By optimizing the ML models with these selected features and testing classifiers across various feature combinations, we find that model performance generally improves as additional features are incorporated. Overall, all five algorithms yield an F1-score (the harmonic mean of precision and recall) >90 per cent even when trained on only 20 per cent of the data set. Among them, the distance-based k-nearest neighbours classifier demonstrates the highest accuracy and stability, establishing it as a robust and effective method for classifying SFGs and AGNs in upcoming large radio continuum surveys.