Spatially Weighted Estimation of Broadacre Crop Growth Improves Gap-Filling of Landsat NDVI

Evans, F.; Shen, Jianxiu

doi:10.3390/rs13112128

Cited by 1 publication

(4 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is a degree of spatial smoothing in the yield hindcasts caused by the use of SWGC for growth curve estimation (see Evans and Shen [48] for discussion of the smoothing effect of SWGC). This affects the precision of the hindcasts, but not their value.…”

Section: Discussionmentioning

confidence: 99%

“…The spatially weighted growth curve (SWGC) estimation method estimates growth curves for each year using data from a spatial neighbourhood around each cell, where the data are weighted according to distance from the central cell using a distance-decay kernel [48]. Spatial weights are applied using a truncated or 'moving window' Gaussian kernel, where the distance weights are set to zero for all cells (x, y) outside of a rectangular region centred on the location for which the growth curve is being estimated.…”

Section: Spatially Weighted Growth Curve Estimationmentioning

confidence: 99%

“…There is a degree of spatial smoothing evident in the predicted maps, when viewed closely. This is due to the spatial smoothing component of spatially weighted growth curve estimation [48], which is propagated into the predicted yields.…”

Section: Yield Hindcastsmentioning

confidence: 99%

“…Because MODIS has higher temporal frequency and more cloud-free images available, methods developed for yield estimation using MODIS-derived phenology may not work for Landsat data. Spatially weighted growth curve (SWGC) estimation is a new method designed specifically for Landsat NDVI to fill spatial and temporal gaps caused by cloud contamination during the growing season [48]. SWGC estimates crop growth curves using data from a local neighbourhood around each cell, where the data are weighted according to geographical distance from the central cell.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Evans

Shen

2021

Remote Sensing

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Spatially Weighted Growth Curve Estimationmentioning

confidence: 99%

Section: Yield Hindcastsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations