Using agrometeorological data to assist irrigation management in oil palm crops: A decision support method and results from crop model simulation

In order to achieve optimum yields in oil palm, management practices should be tailored to the crop site agro-ecological conditions. Nevertheless, oil palm farmers often have to make decisions based on a limited knowledge base. Considering that water management is a critical aspect of oil palm crops, this paper describes an inference method for irrigation decision-making in oil palm supported on soil moisture and vapor pressure deficit data. Under an ideal scenario where this agrometeorological data is available through a Wireless Sensor Network (WSN) at a crop plot resolution, we formulated a method to prevent oil palm farmers to submit their crops to water deficit stress. The inference method was based on a Data Fusion technique called Dempster-Shafer Inference, which is convenient for the use of uncertain data with distinct levels of detail such as those present in a WSN. The outcome of fusing soil moisture and vapor pressure data was inferring the crop state, regarding soil and plant water status, following the concept of Site-specific Agriculture. To evaluate the impact of the method on crop yield, we carried out two simulations. The first one on a WSNs simulator, Castalia, to generate the irrigation decisions according to the site-specific agrometeorological data collected from the WSN. The second one on a crop simulation model, APSIM (Agricultural Production Systems Simulator), to simulate the oil palm plot at the study site under two treatments: plot with irrigation managed by the inference method and plot without irrigation. Results from oil palm crop simulation showed a 27% increase in the production of bunches of fresh fruit between 2016 and 2017 in the treatment with irrigation. The method has the potential for contributing to irrigation decision-support systems and for being useful in yield-intensification rather than crop-extension politics for oil palm and other crops.