Machine learning modeling to predict causes of infectious abortions and perinatal mortalities in cattle.

A plethora of infectious and non-infectious causes of bovine abortions and perinatal mortalities (APM) have been reported in literature. However, due to financial limitations or a potential zoonotic impact, many laboratories only offer a standard analytical panel, limited to a preestablished number of pathogens. To improve the cost-efficiency of laboratory diagnostics, it could be beneficial to design a targeted analytical approach for APM cases, based on maternal and environmental characteristics associated with the prevalence of specific abortifacient pathogens. The objective of this retrospective observational study was to implement a machine learning pipeline (MLP) to predict maternal and environmental factors associated with infectious APM. Our MLP based on a greedy ensemble approach incorporated a standard tuning grid of four models, applied on a dataset of 1590 APM cases with a positive diagnosis that was achieved by analyzing an extensive set of abortifacient pathogens. Production type (dairy/beef), gestation length, and season were successfully predicted by the greedy ensemble, with a modest prediction capacity which ranged between 63 and 73 %. Besides the predictive accuracy of individual variables, our MLP hierarchically identified predictor importance causes of associated environmental/maternal characteristics of APM. For instance, in APM cases that happened in beef cows, season at APM (spring/summer) was the most important predictor with a relative importance of 24 %. Furthermore, at the last trimester of gestation Trueperella pyogenes and Neospora caninum were the most important predictors of APM with a relative importance of 22 and 17 %, respectively. Interestingly, herd size came out as the most relevant predictor for APM in multiparous dams, with a relative importance of 12 %. Based on these and other mix of predicted environmental/maternal and pathogenic potential causes, it could be concluded that implementing our MLP may be beneficial to design a more cost-effective, case-specific diagnostic approach for bovine APM cases at the diagnostic laboratory level.

Institutional and policy analysis of wastewater (re)use for agriculture: case study Hyderabad, India.

Wastewater constitutes an alternative water source for the irrigation sector. To fully benefit from it, and reduce possible adverse effects on public health and the environment, we need to look at the regulation of the practice. A prerequisite for this is an institutional analysis, and the points to consider are the institutional mandates. We used the city of Hyderabad, India, as a case study. There, irrigation with wastewater is not supported or recognized, but it happens in practice. It takes place in an indirect and unplanned way. Institutions fail at enforcing regulations, and little attention is given to formalization of the practice. With this article, we aim to untangle the institutional setup, and by doing so, identify the constraints surrounding development of a formal practice. Ultimately, we aim at contributing to the discussion on the agricultural use of wastewater.

Impact of groundwater markets in India on water use efficiency: a data envelopment analysis approach.

In the hard rock areas of India, overdraft of groundwater has led to negative externalities. It increased costs of groundwater irrigation and caused welfare losses. At the same time informal groundwater markets are slowly emerging and are believed to improve water distribution and to increase water use efficiency in the irrigation sector. These claims are evaluated in this study. For this purpose data was collected from a sample containing three different groups of water users: water sellers, water buyers and a control group of non-traders. First the socio-economic characteristics of these groups are compared. Then the efficiency of water use of the three groups is studied using Data Envelopment Analysis. The results indicate that groundwater markets provide resource poor farmers access to irrigation water, giving them the opportunity to raise their productivity. Water buyers are furthermore shown to be most efficient in their water use, while water sellers are also shown to be more efficient than the control group. The differences in efficiency between the groups are statistically significant. The demonstrated potential of groundwater markets to improve the efficiency of water use and to increase equity in resource access should be taken into account by the Indian government when deciding on their attitude towards the emerging groundwater markets.

Efficiency in milk production on Reunion Island: dealing with land scarcity.

This paper aims to analyze efficiency on dairy farms in Reunion Island, a French overseas district located in the Indian Ocean. On this island, dairy farming is promoted with financial and technical support from the European Union, with the French and local governments aiming at reducing dependency on imports of milk powder and dairy products and creating employment. A critical factor for increasing the local milk production is the limited availability of arable land because of the small size and the volcanic nature of the island. In this paper, we study the efficiency levels of dairy production on 34 farms by using a data envelopment analysis approach. The average technical efficiency score of farms, assuming constant returns to scale, was 0.927, with 19 out of 34 farms not being efficient. The technical efficiency with a variable returns to scale specification was 0.951. The efficiency with which farmers used their land (subvector efficiencies) was estimated in a second model. The average subvector efficiencies calculated with constant returns to scale and variable returns to scale models were lower than the technical efficiencies. The farmers on the efficiency frontier had a relatively higher milk production, milk production per cow, and land surface than those who were less efficient. A policy promoting better use of the land on inefficient farms should increase the milk production-to-land ratio. Possible on-farm strategies are improved feeding systems, farms having their own heifer breeding, and improved genetics.