Testing spatial out-of-sample area of influence for grain forecasting models

We examine the factors that determine if a grain forecasting model fit to one region can be transferred to another region. Prior research has proposed examining the area of applicability (AoA) of a model based on structurally similar characteristics in the Earth Observation predictors and weights based on the model derived feature importance. We expand on and evaluate this approach in the context of grain yield forecasting in Sub-Saharan Africa. Specifically, we evaluate an AoA methodology established for generating raster surfaces and apply it to vector supported grain data. We fit a series of ensemble tree models both within single countries and across multiple sets of countries and then test those models in countries excluded from the training set. We then calculate and decompose AoA measures and examine several different performance metrics. We find that the spatial transfer accuracy does not vary across season but does vary by average rainfall and across high, medium, and low yielding regions. In general, areas with higher yields and medium to high average rainfall tend to have higher accuracy for both model training and transfer. Finally, we find that fitting models with multiple countries provides more accurate out-of-sample estimates when compared to models fitted to a single country

Context (archaeology · Econometrics · Geography · Raster graphics · Sample (material · Set (abstract data type · Statistics · Transfer (computing · Climate change impacts on agriculture · Computer Science · Land Use and Ecosystem Services · Mathematics · Spatial and Panel Data Analysis · Artificial Intelligence

• A Non-Stationary 1981–2012 AVHRR NDVI3g Time Series

  Open Access•Jorge Enrique Dí­az Pinzón, Jorge Pinzon et al.•Remote Sensing•2014

  Incluir item

• The climate hazards infrared precipitation with stations—a new environmental record for monitoring extremes

  Open Access•Chris Funk, Pete Peterson et al.•Scientific Data•2015

  Incluir item

• Overview of the radiometric and biophysical performance of the Modis vegetation indices

  Open Access•Alfredo Huete, Kamel Didan et al.•Remote Sensing of Environment•2002

  Incluir item

• Bootstrap-Based Improvements for Inference with Clustered Errors

  A Colin Cameron, Jonah B Gelbach et al.•The Review of Economics and…•2008

  Incluir item

• Using out-of-sample yield forecast experiments to evaluate which earth observation products best indicate end of season maize yields

  Open Access•Frank Davenport, Laura Harrison et al.•Environmental Research Letters•2019

  Incluir item

• Sending out an SOS

  Open Access•Frank Davenport, Shraddhanand Shukla et al.•Environmental Research Letters•2021

  Incluir item