Predicting site-specific economic optimal nitrogen rate using machine learning methods and on-farm precision experimentation

Abstract

Applying at the economic optimal nitrogen rate (EONR) has the potential to increase nitrogen (N) fertilization efficiency and profits while reducing negative environmental impacts. On-farm precision experimentation (OFPE) provides the opportunity to collect large amounts of data to estimate the EONR. Machine learning (ML) methods such as generalized additive models (GAM) and random forest (RF) are promising methods for estimating yields and EONR. Twenty OFPE N trials in wheat and barley were conducted and analyzed with soil, terrain and remote-sensed variables to address the following objectives: (1) to quantify the spatial variability of winter crops yield and the yield response to N using OFPE, (2) to evaluate and compare the performance of GAM and RF models to predict yield and yield response to N and, (3) to quantify the impact of soil, crop and field characteristics on the EONR estimation. Machine learning techniques were able to model wheat and barley yield with an average error of 13.7% (624 kg ha−1). However, similar yield prediction accuracy from RF and GAM resulted in widely different economic optimal nitrogen rates. Across sites, soil available phosphorus and soil organic matter were the most influential variables; however, the magnitude and direction of the effect varied between fields. These indicate that training a model using data coming from different fields may lead to unreliable site-specific EONR when it is applied to another field. Further evaluation of ML methods is needed to ensure a robust automation of N recommendation while producers transition into the digital ag era.

Big Data and Machine Learning: What Is It and Can We Use It for 4R Nutrient Management?

“…There is much to learn and improve in this area of ML prediction. Researchers have concluded that as technology improves, there is great opportunity to employ ML, but today more research is required to widely deploy it for N rate predictions (de Lara et al., 2023; Chlingaryan et al., 2018).

…”

“…A 2022 study in of canola production in Canada found that using ML models could reasonably predict optimal N rates for split applications when historical and current weather conditions were included in the model (Wen et al., 2022). However, a Nebraska study in corn found that ML models built from data in one field could not be used to accurately predict N rates in other fields (de Lara et al., 2023). There is much to learn and improve in this area of ML prediction.…”

Complete Issue

“…A 2022 study in of canola production in Canada found that using ML models could reasonably predict optimal N rates for split applications when historical and current weather conditions were included in the model (Wen et al, 2022). However, a Nebraska study in corn found that ML models built from data in one field could not be used to accurately predict N rates in other fields (de Lara et al, 2023). There is much to learn and improve in this area of ML prediction.…”

“…There is much to learn and improve in this area of ML prediction. Researchers have concluded that as technology improves, there is great opportunity to employ ML, but today more research is required to widely deploy it for N rate predictions (de Lara et al, 2023;Chlingaryan et al, 2018).…”

Bias in economic evaluation of variable rate application based on geographically weighted regression models with misspecified functional form

“…One can then plug in site-specific soil/ field characteristics to the estimated model to represent site-specific yield response functions. A variety of statistical methods are employed within this framework, including spatial econometrics (Anselin et al, 2004;Liu et al, 2006) and various machine learning techniques like random forests (Krause et al, 2020;Lara et al, 2023), convolutional neural networks (Barbosa et al, 2020), and causal forests (Kakimoto et al, 2022). The second approach is characteristic-agnostic, represented by geographically weighted regression (GWR).…”