Use of an Empirical Model to Estimate Leaf Wetness Duration for Operation of a Disease Warning System Under a Shade in a Ginseng Field

Approaches for the Prediction of Leaf Wetness Duration with Machine Learning

The prediction of leaf wetness duration (LWD) is an issue of interest for disease prevention in coffee plantations, forests, and other crops. This study analyzed different LWD prediction approaches using machine learning and meteorological and temporal variables as the models’ input. The information was collected through meteorological stations placed in coffee plantations in six different regions of Costa Rica, and the leaf wetness duration was measured by sensors installed in the same regions. The best prediction models had a mean absolute error of around 60 min per day. Our results demonstrate that for LWD modeling, it is not convenient to aggregate records at a daily level. The model performance was better when the records were collected at intervals of 15 min instead of 30 min.

Leaf Wetness Duration Models Using Advanced Machine Learning Algorithms: Application to Farms in Gyeonggi Province, South Korea

Leaf wetness duration (LWD) models have been proposed as an alternative to in situ LWD measurement, as they can predict leaf wetness using physical mechanism and empirical relationship with meteorological conditions. Applications of advanced machine learning (ML) algorithms in the development of empirical LWD model can lead to improvements in the LWD prediction. The current study developed LWD model using extreme learning machine, random forest method, and a deep neural network. Additionally, performances of these ML-based LWD models are evaluated and compared with existing models. Observed LWD and meteorological variable data are obtained from nine farms in South Korea. Temporal and geographical information were also used. Additionally, the priorities of the employed variables in the development of the ML-based LWD models were analyzed. As a result, the ML-based LWD models outperformed the existing models; the random forest led to the best performance for LWD prediction among the tested LWD models. Strengths of associations between input variables and leaf wetness were relative humidity, short wave radiation, air temperature, hour, latitude, longitude, and wind speed in descending order. Uses of the geographical and time information in development of LWD model can improve the performance of LWD model.

Modelling the impacts of pests and diseases on agricultural systems

The improvement and application of pest and disease models to analyse and predict yield losses including those due to climate change is still a challenge for the scientific community. Applied modelling of crop diseases and pests has mostly targeted the development of support capabilities to schedule scouting or pesticide applications. There is a need for research to both broaden the scope and evaluate the capabilities of pest and disease models. Key research questions not only involve the assessment of the potential effects of climate change on known pathosystems, but also on new pathogens which could alter the (still incompletely documented) impacts of pests and diseases on agricultural systems. Yield loss data collected in various current environments may no longer represent a adequate reference to develop tactical, decision-oriented, models for plant diseases and pests and their impacts, because of the ongoing changes in climate patterns. Process-based agricultural simulation modelling, on the other hand, appears to represent a viable methodology to estimate the impacts of these potential effects. A new generation of tools based on state-of-the-art knowledge and technologies is needed to allow systems analysis including key processes and their dynamics over appropriate suitable range of environmental variables. This paper offers a brief overview of the current state of development in coupling pest and disease models to crop models, and discusses technical and scientific challenges. We propose a five-stage roadmap to improve the simulation of the impacts caused by plant diseases and pests; i) improve the quality and availability of data for model inputs; ii) improve the quality and availability of data for model evaluation; iii) improve the integration with crop models; iv) improve the processes for model evaluation; and v) develop a community of plant pest and disease modelers.