Long-Term Hindcasts of Wheat Yield in Fields Using Remotely Sensed Phenology, Climate Data and Machine Learning

Abstract

Satellite remote sensing offers a cost-effective means of generating long-term hindcasts of yield that can be used to understand how yield varies in time and space. This study investigated the use of remotely sensed phenology, climate data and machine learning for estimating yield at a resolution suitable for optimising crop management in fields. We used spatially weighted growth curve estimation to identify the timing of phenological events from sequences of Landsat NDVI and derive phenological and seasonal climate metrics. Using data from a 17,000 ha study area, we investigated the relationships between the metrics and yield over 17 years from 2003 to 2019. We compared six statistical and machine learning models for estimating yield: multiple linear regression, mixed effects models, generalised additive models, random forests, support vector regression using radial basis functions and deep learning neural networks. We used a 50-50 train-test split on paddock-years where 50% of paddock-year combinations were randomly selected and used to train each model and the remaining 50% of paddock-years were used to assess the model accuracy. Using only phenological metrics, accuracy was highest using a linear mixed model with a random effect that allowed the relationship between integrated NDVI and yield to vary by year (R2 = 0.67, MAE = 0.25 t ha−1, RMSE = 0.33 t ha−1, NRMSE = 0.25). We quantified the improvements in accuracy when seasonal climate metrics were also used as predictors. We identified two optimal models using the combined phenological and seasonal climate metrics: support vector regression and deep learning models (R2 = 0.68, MAE = 0.25 t ha−1, RMSE = 0.32 t ha−1, NRMSE = 0.25). While the linear mixed model using only phenological metrics performed similarly to the nonlinear models that are also seasonal climate metrics, the nonlinear models can be more easily generalised to estimate yield in years for which training data are unavailable. We conclude that long-term hindcasts of wheat yield in fields, at 30 m spatial resolution, can be produced using remotely sensed phenology from Landsat NDVI, climate data and machine learning.

A three-part coupled statistical and physical model to monitor water quality parameters governing disinfection byproduct risk at an urban drinking water intake

“…To further validate the temperature model, a hindcast, where the model is run and compared to a concrete historic event (Evans and Shen, 2021), was performed for the random forest temperature model from 2016 to 2019. Further, model projections for 2020 are included and are OOB as this year was not included in the test or training sets.…”

Time Phase Selection and Accuracy Analysis for Predicting Winter Wheat Yield Based on Time Series Vegetation Index

“…Therefore, the CSI method makes our research more accurate in predicting regional wheat yield. Evans et al used the spline interpolation method to smooth the data curve in their study for the subsequent winter wheat yield prediction [50]. Some studies have used interpolation to process data to obtain a coherent, complete dataset to predict the extreme yield loss of crops [51].…”

Nonlinear Responses of Vegetation Phenology to Climate Change and Urbanization: A Case Study in Beijing, China

“…Therefore, research on the analysis of the non-linear relationships between vegetation phenology and external environmental changes is gradually increasing [12], [13], [14]. Meanwhile, non-linear models have been used for vegetation phenology prediction, which are suitable for exploring the non-linear impact of large-scale climate changes on phenology [15], and the prediction accuracy using non-linear models is higher [16], [17]. Motivated by these studies of using non-linear models to predict phenology, this research proposes the application of the generalized additive model (GAM) to analyze the non-linear relationships between vegetation phenology, climate change and urbanization, and evaluate the feasibility of vegetation phenology prediction.…”