On-The-Go Variable Rate Fertilizer Application Method for Rice Through Classification of Crop Nitrogen Nutrition Index (NNI)

Abstract

The standard practice among rice farmers in Malaysia is to apply fertilizer using a single application rate for the whole field. However, fertility conditions vary across the field. The excess use of fertilizer leads to increased input cost and can be damaging to the environment. The focus of this research was to develop a method to apply fertilizer on-the-go while sensing the crop nutrient status of rice plants. A machine learning approach was used to develop a crop nitrogen status prediction model. The model used spectral data from an active canopy reflectance sensor and several vegetation indices as inputs. The model was then incorporated into an on-the-go variable rate fertilizer application system. System performance was then evaluated in the field. The results from this work showed that the model had and accuracy of 83% in classifying the nitrogen status of the rice plants. The results also showed that our method was able to save up to 20% fertilizer use while maintaining yield. These findings are important for large estate farmers who are looking to increase productivity and efficiency.

Plant Nutrition—New Methods Based on the Lessons of History: A Review

“…There are important variable technologies applied to VRF to monitor the soil-nutrient status, yield, and harvest-related information [ 274 ]. High-throughput crop phenotyping technologies, such as remote sensing-based platforms (unmanned aerial vehicles (URVs), red-green-blue (RGB) cameras, normalised difference vegetation index (NDVI), and microwave back scattering) and map-based platforms (geographical information system (GIS), and global positioning system (GPS) maps) are used for variable-rate fertilisation prescription maps and site-specific crop and soil management [ 268 , 272 , 275 , 276 , 277 ]. For instance, NDVI and VRF are used to specify the amount of fertiliser and the location of the application [ 278 ].…”

“…For instance, NDVI and VRF are used to specify the amount of fertiliser and the location of the application [ 278 ]. Optical sensors (GreenSeeker’s and active canopy reflectance sensors) are used to estimate the N status in rice, soybean and corn [ 275 ]. Another wide range of spectra indices (i.e., NDVI, leaf area index (LAI), ratio vegetation index (RVI), chlorophyll index (SPAD), and NNI) is used to predict the N status and crop requirements based on real-time growth information [ 267 , 272 ].…”

Technology Application in Smart Farming Agriculture: A Survey

“…Technology of fertigation uses the injected fertiliser inside the irrigation system to water plants through the field. Malaysian farmers that plant rice usually use fertilisers by one measurement to be used in the overall crop field (Abu Bakar et al, 2021). It is important to apply scientific study in farming such as the quality of the seed and water, and the protection of the plant such as the agriculture house (Sharma et al, 2021).…”

Variable-rate application of fertiliser – a new tool for farm system and environmental performance?

“…One technology that has been developed to contribute to this challenge is variablerate application (VRA) of fertiliser. Internationally, this technology has been developed for use in many crops e.g., wheat (Robertson et al, 2012), rice (Bakar et al, 2021) and maize (Lan et al, 2008, Sharma andIrmak 2020), but rarely in pastures (Hills et al, 2014;Corrêdo et al, 2019). In New Zealand, it has been developed for application of fertilisers to hill country pastures from aircraft (Morton et al, 2016, White et al, 2017Grafton et al, 2021) and is now being developed for ground spreading of urea on dairy farms (Wigley et al, 2017).…”