Suitability of different machine learning algorithms for the classification of the proportion of grassland-based forages at herd-level using mid-infrared spectral information from routine milk control.

As the call for an international standard for milk from grassland-based production systems continues to grow, so too do the monitoring and evaluation policies surrounding this topic. Individual stipulations by countries and milk producers to market their milk under their own grass-fed labels include a compulsory number of grazing days per year, ranging from 120 d for certain labels to 180 d for others, a specified amount of herbage in the diet or a prescribed dietary proportion of grassland-based forages (GBF) fed and produced on farm. As these multifarious policy and label requirements are laborious and costly to monitor on farm, fast economical proxies would be advantageous to verify the proportion of GBF consumed by the cows in the final product. With this in mind, we employed readily available mid-infrared spectral data (n = 1132 spectra) from routine milk controls to develop binary classification models for 4 main feed groups from a primarily forage-based diet: Total GBF (≥50% n = 955, ≥ 75% n = 599, ≥ 85% n = 356), pasture (≥20% n = 451, ≥ 50% n = 284, ≥ 70% n = 152), fresh herbage (pasture + fresh herbage indoor feeding, ≥ 20% n = 517, ≥ 50% n = 325, ≥ 70% n = 182) and whole plant corn (fresh + conserved) (≥10% n = 646, ≥ 30% n = 187), the latter as a negative control. We compared 4 machine learning methods to assess which statistical model performs best at discriminating these classes. Three of these models have not yet been tested for herd-level dietary proportion classification and all 4 follow completely different approaches: least absolute shrinkage and selection operator (LASSO), partial least squares discriminant analysis (PLS-DA), random forest (RF) and support vector machines (SVM). Seasonality has been a missing element from previous dietary herbage proportion classification models. As grazing and fresh herbage indoor feeding are highly dependent on the season, we developed an indicator to incorporate seasonality in a consistent, unbiased manner into our models. We also tested 3 sets of covariates. The first set included only mid-infrared spectra derived data, the second included mid-infrared spectra derived data plus seasonality indices and the third included mid-infrared spectra derived data, seasonality indices and additional herd specific information (DIM, breed and parity). Of the 4 machine learning algorithms tested for the binary classification of GBF proportion at herd level, LASSO and PLS-DA performed best according to evaluation metrics; however, the RF and SVM models were not far behind the best performing model evaluation metrics in each feed category. Our best performing model, the LASSO model containing seasonality indices and herd specific information, classified total GBF ≥50% with an accuracy of 78.6%, precision of 85.1%, sensitivity of 90.6%, specificity 14.1% and F1 score (harmonic mean of precision and sensitivity) of 87.7%, this was very similar to the PLS-DA model. Our results suggest that in general LASSO and PLS-DA machine learning algorithms perform better for dietary GBF classification than RF or SVM algorithms.

Machine learning-based assessment of long-term climate variability of Kerala.

Studies on historical patterns of climate variables and climate indices have attained significant importance because of the increasing frequency and severity of extreme events worldwide. While the recent events in the tropical state of Kerala (India) have drawn attention to the catastrophic impacts of extreme rainfall events leading to landslides and loss of human lives, a comprehensive and long-term spatiotemporal assessment of climate variables is still lacking. This study investigates the long-term trend analysis (119 years) of climate variables at 5% significance level over the state using gridded datasets of daily rainfall (0.25° × 0.25° spatial resolution) and temperature (1° × 1° spatial resolution) at annual and seasonal scales (south-west monsoon, north-east monsoon, winter and summer). Five trend analysis techniques including the Mann-Kendall test (MK), three modified Mann-Kendall tests and innovative trend analysis (ITA) test were performed in the study. It is evident from the trend analysis results that more than 83% of grid points were showing negative trends in annual and south-west monsoon season rainfall series (at a mean rate of 39.70 mm and 28.30 mm per decade respectively). All the trend analysis tests identified statistically significant increasing trends in mean and maximum temperature at annual and seasonal scales (0.10 to 0.20 °C/decade) for all grids. The K-means clustering algorithm delineated 59 grid points into five clusters for annual rainfall, illustrating a clear geographical pattern over the study area. There is a clear gradient in rainfall distribution and concentration inside the state at annual as well as seasonal scales. The majority of annual rainfall is concentrated in a few months of the year. That may lead the state vulnerable to water scarcity in non-rainy seasons.

Water footprint: applying the water footprint assessment method to Australian agriculture.

BACKGROUND: Water footprint assessment is essential for the evaluation of water scarcity that considers both direct and indirect water consumption along the supply chain. This paper presents the estimation of water footprint for locally grown fruits and vegetables in Australia. Water footprint was calculated based on the framework developed in the Water Footprint Assessment Manual for the crops which are the most practicable to grow in Australia. Nine different crops (apples, grapes, tomatoes, oranges, peaches/nectarines, cherries, potatoes, carrots/turnips and almonds) in the agricultural industry were selected and identified as the most water-consumptive crop and least water-consumptive crop. For each type of crop, the three main water footprint components (blue, green, and grey water) were calculated. RESULTS: It was found that almond had the highest water footprint (6671.96 m3  ton-1 ) and tomato had the lowest water footprint (212.24 m3  ton-1 ) in Australia. From the global comparison, it is revealed that total water footprint for Australian crops is much higher than the corresponding international average values, except for tomatoes, potatoes and almonds. Also, almonds had the highest water footprint among the nine crops investigated. CONCLUSION: The study provides an insight into future sustainable cropping patterns in Australia, which suggest that tomatoes, carrots/turnips, potatoes and apples should continue to be grown in Australia, whereas stone fruit (e.g., almonds) should no longer be grown because of its high water footprint. © 2020 Society of Chemical Industry.

Socio-economic inequality in health service utilisation: Does accounting for seasonality in health-seeking behaviour matter?

Seasonal variation exists in disease incidence. The variation could occur across the different regions in a country. This paper argues that using national household data that are not adjusted for seasonal and regional variations in disease incidence may not be directly suitable for assessing socio-economic inequality in annual outpatient service utilisation, including for cross-country comparison. In fact, annual health service utilisation may be understated or overstated depending on the period of data collection. This may lead to miss-estimation of socio-economic inequality in health service utilisation depending, among other things, on how health service utilisation, across geographical areas, varies by socio-economic status. Using a nationally representative dataset from South Africa, the paper applies a seasonality index that is constructed from the District Health Information System, an administrative dataset, to annualise public outpatient health service visits. Using the concentration index, socio-economic inequality in health service visits, after accounting for seasonal variations, was compared with that when seasonal variations are ignored. It was found that, in some cases, socio-economic inequality in outpatient health service visits depends on the socio-economic distribution of the seasonality index. This may justify the need to account for seasonal and geographical variations.