NODES - SPOKE 6 Project FORMIDABILÆ - D4.1 Report on heat stress monitoring and quantification

The aim of this study was to (1) quantify how a heat wave affects milk-yield resilience in dairy cows and (2) develop a model to predict daily milk yield during heat stress. Data from 305 cows across four commercial farms (Arborea, Italy) were analyzed during a heat wave (12–19 August 2022). Ten resilience indicators were calculated (milk loss, recovery rate, stress duration, etc.). Results showed that heat stress reduced milk yield in all cows. Early-lactation cows were the most resilient, showing smaller percentage losses and faster recovery. High-producing cows lost more milk in absolute terms, although the percentage loss was similar to other groups. Multiparous cows displayed slightly better recovery milk yield than primiparous cows. Temperature–Humidity Index (THI) correlated with milk loss and recovery time. For prediction, four models were tested (GLM, Random Forest, GBM, XGBoost) using THI data and recent milk-yield history. The GLM performed best, achieving the lowest prediction error and showing superior external validation on an independent farm. A shiny web application was developed to forecast milk yield during heat waves, supporting proactive farm decision-making. This document is a deliverable of the project FORMIDABILÆ ("Forage system to make resilient Maize, Dairy and Biogas supply chains for a Lasting Agricultural Ecosystem"), which promotes approaches aimed at improving the smart, resilient, circular and diversified farm to ensure food security and social economic sustainability of dairy food chains with the aim of reducing greenhouse gas emissions in this sector. This document is part of the project NODES which has received funding from the MUR – Missione 4, Componente 2, Investimento 1.5 – Creazione e rafforzamento di “Ecosistemi dell’innovazione”, costruzione di “leader territoriali di R&S'' – del PNRR funded by the European Union - NextGenerationEU with grant agreement no. ECS00000036