GeoPython 2021

Improved Crop Yield Prediction through Spatio-Temporal Analysis of Agricultural Data
2021-04-23, 14:00–14:30, Track 1

Precision agriculture has seen a remarkable progress over the last decade or so with its primary goal being accurate prediction of crop yield. This talk provides an overview of efforts in SFI's funded project CONSUS whereby agricultural data obtained from a commercial agronomy service company is used to derive significant insights for crop yield prediction.

Over the past decade or so agricultural technology has seen remarkable progress giving birth to precision agriculture whereby huge quantities of useful data can be extracted from Internet of Things, sensors, satellites, weather stations, robots, farm equipment, agricultural laboratories, farmers, government agencies etc. In this talk I will highlight various aspects of putting this data to practical use towards enhanced decision-making in crop management practices leading towards crop yield optimization while also helping towards preservation of the environment. This is done by means of modern machine learning methods that treat the data as being part of a a complex system of interconnected variables and conditions with the final output enabling predictions of crop yield to be made. A special emphasis is given to spatio-temporal aspects of agricultural data, and how it is incorporated into our crop yield prediction algorithms.

Some analysis of various agricultural fields and corresponding spatio-temporal variables such as weather, soil properties, topographical factors is also performed in order to motivate the underlying theory for our proposed methodology.