Adjustment Pattern of pH Using Random Forest Regressor for Crop Modelling of NFT Hydroponic Lettuce

Abstract IoT makes it possible to automatically adjust pH based on sensor numerical data for NFT hydroponic lettuce. In this research, we use sensors of light intensity, farm temperature , humid reservoir level the outside farm, at Kartika Farm and Turus Asri. Data were taken five cropping periods. We got different adjustment pattern these Total Dissolved Solids (TDS) control. Furthermore, Farm’s was from a kilogram ingredient seven holes lettuces while Asri ten lettuces. Economically, harvests more benefits than modeling using random forest regression. The result showed that important variable is water level, TDS green house humidity. an accurate value model 78,37% with MAE MSE consecutively 0.19 0.15.