Programação

Espanol

Palestra 1: Professor Carlos Holbig - Universidade de Passo Fundo

Título: Digital technology in agriculture: tools for decision making

Resumo: The challenge of agriculture today is to feed the world while being economical, environmentally, and sociable sustainable. The seasonal weather variability is well known as one of a primary source of crop production risks. The main causes of crop failures are associated with either a lack of moisture or excess of rainfall. Other production risk sources, such as insect pest/disease incidence, are also highly related to climate variability. In addition, the challenges posed by climate variability and climate change are increasingly important. Efforts have been made to develop solutions, based on crop and insect pest/disease simulation models, to help growers to make decisions, understand the agricultural phenomena and reduce the costs with unnecessary use of pesticides while increasing the sustainability of their operations as well as minimizing the risks. The work in our group constitutes an attempt to develop a software suite and frameworks for the simulation of both generic insect pest and disease models that can be easily coupled with crop models aiming to improve crop yield estimation under different scenarios. Our experience has shown that helping farmers to use effectively forecast and seasonal climate forecasts for reducing production risks and adapting management practices to the expected climate also enhances their ability to face potential climate impacts on crop production.

Palestra 2: Professor Marilton S. de Aguiar - Universidade Federal de Pelotas

Título: Machine learning applied to the identification and infestation prediction of fruit fly in intelligent traps

Resumo: The integrated pest management is an approach that seeks to keep pests always below the level at which they cause damage to crops. A technique widely employed in monitoring the population of pests is based on the use of traps and consists in regular field visits to make visual observations of this traps by a human operator. The use of pesticides for controlling the population growth of a given pest is the most commonly used technique. One of the reasons for this is the response time that such method has, acting quickly and eliminating the threat to the crops. However, pesticides are known for their risk in the health of consumers, farmers, and pesticide applicants. This lecture aims to present the latest research related to the development of an intelligent insect identification trap using deep and conventional machine learning as well as prediction of infestation using climate data. At the end, it can be stated that it is possible to reduce the use of pesticides in crops, since it is no longer necessary to apply in an entire crop as a preventive action, thus avoiding waste. Furthermore, there is a reduction of crop loss, since infestations are avoided.