Forest plantations, particularly those cultivating eucalyptus, are crucial for the wood and paper industries. However, growers often encounter challenges, such as high plant mortality, after transplantation, primarily due to water deficits. While semi-mechanized systems combining machinery and manual labor are commonly used, they incur substantial operational costs. Fully mechanized automatic irrigation systems offer a cost-effective alternative that is gaining traction in adoption. This project aimed to develop an automatic system for eucalyptus plant detection to facilitate effective irrigation management. Two real-time eucalyptus plant detection models were built and trained using acquired field images and YOLOv8 and YOLOv5 neural networks. Evaluation metrics, such as precision, recall, mAP-50, and mAP50-95, were used to compare model performance and select the best option for localized irrigation automation. The YOLOv8 model had a mean detection precision of 0.958 and a mean recall of 0.935, with an mAP-50 of 0.974 and an mAP50-95 of 0.836. Conversely, the YOLOv5 model had a mean detection precision of 0.951 and a mean recall of 0.944, with an mAP-50 of 0.972 and an mAP50-95 of 0.791. Both models could serve as support tools for the real-time automation of localized irrigation for young eucalyptus plants, contributing to the optimization of irrigation processes in forest plantations.
Western Bahia is a region widely recognized for its significance in large-scale agricultural production, being one of the mainstays of the local economy. However, agricultural activities in this area are often challenged by extended periods of low precipitation, posing a constant threat to the productivity of major crops. Deep concerns are raised by unpredictability of rainfall, especially in February during the critical period of crops, which encompasses the flowering and/or grain filling stages of most crops in the region. In this scenario, this study assumes a central role in search for answers. Thus, this paper aimed to analyze the behavior of spatial and temporal variability of rainfall in the Western region of Bahia. The research focused on the month of February due to its critical relevance to the life cycle of local crops and its direct influence in agricultural productivity. Rainfall data were obtained from the stations network of the National Water Agency (ANA) through the Hydroweb platform for the period from 1986 to 2015. The Rain Anomaly Index (RAI) for the month of February was then calculated using equations developed by Rooy (1965). To analyze the space-time variability of drought events in their different intensities, RAI maps were generated containing eight categories ranging from extremely wet to extremely dry, for the measurement and classification of rainfall anomalies in relation to the historical average. The results revealed that throughout the analyzed period, approximately 53.33% of the February months exhibited negative anomalies, denoting drought events ranging from mild to extreme, while approximately 30% of the months displayed positive anomalies, indicating moisture levels ranging from low to extremely wet. Notably, in the years with the most significant negative anomalies (drought events), there was a predominance of spatial variability from east to west, with the lowest negative anomalies on the western side and the highest on the eastern side of the region. On the other hand, positive anomalies (wet events) exhibited a predominance of spatial variability from south to north in the region. This study provides valuable insights for the agricultural sector, water resource planning, and environmental management. It underscores the importance of adaptive strategies to address climatic fluctuations and ensure the sustainability of agricultural production in the Western Region of Bahia.