Reference evapotranspiration (ET₀) is one important agrometeorological parameter for hydrological studies and climate risk zoning. ET₀ calculation by the FAO Penman–Monteith method requires several input data. However, the availability of climate data has been a problem in many places around the world, so the study of scenarios with different combinations of climate data has become essential. The aim of this study was to evaluate the performance of artificial neural network (ANN), random forest (RF), support vector machine (SVM), and multiple linear regression (MLR) approaches to estimate monthly mean ET₀ with different input data combinations and scenarios. Three scenarios were evaluated: at the state level, where all climatological stations were used (Scenario I–SI), and at the regional level, where the Minas Gerais state was divided according to the climatic classifications of Thornthwaite (Scenario II–SII) and Köppen (Scenario III–SIII). ANN and RF performed better in ET₀ estimation among the models evaluated in the SI, SII, and SIII scenarios with the following data combinations: (i) latitude, longitude, altitude, month, mean, maximum and minimum temperature, and relative humidity and (ii) latitude, longitude, altitude, month, mean temperature, and relative humidity. SVM and MLR models are recommended for all scenarios in situations with limited climatic data where only air temperature and relative humidity data are available. The results and information presented in this study are important for the agricultural chain and water resources in Minas Gerais state.

This research project aims at identifying a new network of routes and historical itineraries for the development and promotion of rural tourism in the Tuscany Region, by promoting forms of sustainable mobility in rural areas, particularly marginal ones. Religious tourism is defined as tourism, which includes visits to religious sites such as shrines, churches, abbeys, hermitages and sacred places; such places are an attraction for their religious essence as well as their artistic and cultural beauty. The ancient obsolete road system, which often survives as an archaeological relic as a precursor of the present road system, especially in rural areas, is more widespread than a layman would think. The paper refers the results of the study aimed at recovering the entire historical road that allowed pilgrims and travelers to reach La Verna (a place where St. Francis received the Stigmata) coming from Florence.

Climate change is causing an increase in global temperatures, with significant impacts on dairy production. This systematic review analyzes the challenges of new climate scenarios, focusing on the resilience and adaptation strategies of dairy systems. The PRISMA methodology guided the review process using the Scopus and Web of Science databases. After applying exclusion criteria, 30 articles published between 2015 and 2025 were selected. The studies included analyses of the effects of heat stress on animal parameters (I), socioeconomic parameters (II), and technological adaptation tools (III) in various geographic regions. Most research over the last decade addresses category (I), with a greater concentration in the Northern Hemisphere. The Temperature Humidity Index (THI) emerged as the main indicator of heat stress, associated with the physiological responses of dairy cattle. Heat stress reduces milk production, feed intake, reproductive performance, and overall animal health, often leading to increased slaughter rates. Adaptation strategies include genetic selection for heat tolerance, improved environmental monitoring, cooling technologies, and optimized nutritional and management practices, applicable to both pasture and feedlot systems. Despite being among the main producers, studies on the topic in South American countries are still scarce in the literature.

The main challenge in milk production has been to maintain a focus on efficient processes that enhance production outcomes while aligning with animal welfare and sustainability and being valued by society. As an alternative to improve cow welfare in production and provide better handling of the waste generated by the activity, the system called the compost-bedded pack barn (CBP) has been widely adopted in countries with temperate climates and higher milk production. This CBP has been attracting global interest, including from countries with tropical and subtropical climates, such as Brazil, where many producers have started to use it due to the response in terms of milk productivity. A CBP can be designed either in (a) an open facility with natural ventilation or a positive-pressure ventilation system or (b) totally closed facilities, equipped with negative-pressure ventilation systems and permanent thermal control. The latter system is being implemented in Brazil, despite insufficient knowledge about its efficiency. The objective of this study was, through a review, to gather and describe the most recent information on the use of open and closed CBP systems for dairy cattle housing, mainly covering how it is applied in tropical climate regions. To achieve the proposed objective, this review study included the following topics related to CBPs: (i) implementation, (ii) bedding, (iii) general construction and architectural characteristics, and (iv) ambient thermal conditioning. Knowledge gaps and directions for future research are also identified here.

The objective of this study was to characterize the dependence and spatial distribution of bedding attributes in an open compost-bedded pack barn (CBP) system with positive pressure ventilation during the winter period in Brazil. The study was conducted in July 2021, in the Zona da Mata region, Minas Gerais, Brazil. The bedding area (shavings and wood sawdust) was divided into a mesh with 44 equidistant points. At each point, the bedding temperature at the surface (t_B-sur) and at a depth of 0.2 m (t_B-20) and the air velocity at bedding level (v_air,B) were measured, and bedding samples were collected. The bedding samples were used to determine the moisture level and pH at the surface (M_B-sur e pH_B-sur) and at a depth of 0.2 m (M_B-20 and pH_B-20). The spatial behavior of the variables was evaluated using geostatistics techniques. For all variables, the occurrence of strong spatial dependence was verified. Through the maps, it was observed that t_B-sur, t_B-20, M_B-sur, M_B-20, and v_air,B showed high spatial variability, whereas pH_B-sur and pH_B-20 demonstrated low variation. On the surface, values of t_B-sur < 20 °C and M_B-sur > 60% were observed. At the subsurface, there was a predominance of t_B-20 < 40 °C, M_B-20 > 60%, and pH > 9, which are indications of low bedding composting activity.

The coffee leaf miner (Leucoptera coffeella) is a key pest in coffee-producing regions in Brazil. The objective of this work was to evaluate the potential of machine learning algorithms to identify coffee leaf miner infestation by considering the assessment period and Sentinel-2 satellite images generated on the Google Earth Engine platform. Coffee leaf miner infestation in the field was measured monthly from 2019 to 2023. Images were selected from the Sentinel-2 satellite to determine 13 vegetative indices. The selection of images and calculations of the vegetation indices were carried out using the Google Earth Engine platform. A database was generated with information on coffee leaf miner infestation, vegetation indices, and assessment times. The database was separated into training data and testing data. Nine machine learning algorithms were used, including Linear Discriminant Analysis, Random Forest, Support Vector Machine, k-nearest neighbors, and Logistic Regression, and a principal component analysis was conducted for each algorithm. After optimizing the hyperparameters, the testing data were used to validate the model. The best model to estimate miner infestation was RF, which had an accuracy of 0.86, a kappa index of 0.64, and a precision of 0.87. The developed models were capable of monitoring coffee leaf miner infestation.