Prediction of drought-induced reduction of agricultural productivity in Chile from MODIS, rainfall estimates, and climate oscillation indices

Francisco Zambrano (Corresponding Author), Anton Vrieling, Andy Nelson, Michele Meroni, Tsegaye Tadesse

Research output: Contribution to journalArticleAcademicpeer-review

4 Citations (Scopus)
58 Downloads (Pure)

Abstract

Global food security is negatively affected by drought. Climate projections show that drought frequency and intensity may increase in different parts of the globe. These increases are particularly hazardous for developing countries. Early season forecasts on drought occurrence and severity could help to better mitigate the negative consequences of drought. The objective of this study was to assess if interannual variability in agricultural productivity in Chile can be accurately predicted from freely-available, near real-time data sources. As the response variable, we used the standard score of seasonal cumulative NDVI (zcNDVI), based on 2000–2017 data from Moderate Resolution Imaging Spectroradiometer (MODIS), as a proxy for anomalies of seasonal primary productivity. The predictions were performed with forecast lead times from one- to six-month before the end of the growing season, which varied between census units in Chile. Predictor variables included the zcNDVI obtained by cumulating NDVI from season start up to prediction time; standardised precipitation indices derived from satellite rainfall estimates, for time-scales of 1, 3, 6, 12 and 24 months; the Pacific Decadal Oscillation and the Multivariate ENSO oscillation indices; the length of the growing season, and latitude and longitude. For each of the 758 census units considered, the time series of the response and the predictor variables were averaged for agricultural areas resulting in a 17-season time series per unit for each variable. We used two prediction approaches: (i) optimal linear regression (OLR) whereby for each census unit the single predictor was selected that best explained the interannual zcNDVI variability, and (ii) a multi-layer feedforward neural network architecture, often called deep learning (DL), where all predictors for all units were combined in a single spatio-temporal model. Both approaches were evaluated with a leave-one-year-out cross-validation procedure. Both methods showed good prediction accuracies for small lead times and similar values for all lead times. The mean Rcv2 values for OLR were 0.95, 0.83, 0.68, 0.56, 0.46 and 0.37, against 0.96, 0.84, 0.65, 0.54, 0.46 and 0.38 for DL, for one, two, three, four, five, and six months lead time, respectively. Given the wide range of climates and vegetation types covered within the study area, we expect that the presented models can contribute to an improved early warning system for agricultural drought in different geographical settings around the globe.
Original languageEnglish
Pages (from-to)15-30
Number of pages16
JournalRemote sensing of environment
Volume219
Early online date9 Oct 2018
DOIs
Publication statusPublished - 15 Dec 2018

Fingerprint

climate oscillation
Drought
moderate resolution imaging spectroradiometer
MODIS
Rain
Chile
oscillation
Productivity
drought
climate
rain
Imaging techniques
productivity
rainfall
prediction
census
Linear regression
NDVI
Time series
time series analysis

Keywords

  • Early-warning
  • Drought
  • Agriculture
  • Productivity
  • Prediction
  • Chile
  • MODIS
  • zcNDVI
  • Phenology
  • ITC-ISI-JOURNAL-ARTICLE

Cite this

@article{5ff70faf147c4791976a0b2ce77ff6c1,
title = "Prediction of drought-induced reduction of agricultural productivity in Chile from MODIS, rainfall estimates, and climate oscillation indices",
abstract = "Global food security is negatively affected by drought. Climate projections show that drought frequency and intensity may increase in different parts of the globe. These increases are particularly hazardous for developing countries. Early season forecasts on drought occurrence and severity could help to better mitigate the negative consequences of drought. The objective of this study was to assess if interannual variability in agricultural productivity in Chile can be accurately predicted from freely-available, near real-time data sources. As the response variable, we used the standard score of seasonal cumulative NDVI (zcNDVI), based on 2000–2017 data from Moderate Resolution Imaging Spectroradiometer (MODIS), as a proxy for anomalies of seasonal primary productivity. The predictions were performed with forecast lead times from one- to six-month before the end of the growing season, which varied between census units in Chile. Predictor variables included the zcNDVI obtained by cumulating NDVI from season start up to prediction time; standardised precipitation indices derived from satellite rainfall estimates, for time-scales of 1, 3, 6, 12 and 24 months; the Pacific Decadal Oscillation and the Multivariate ENSO oscillation indices; the length of the growing season, and latitude and longitude. For each of the 758 census units considered, the time series of the response and the predictor variables were averaged for agricultural areas resulting in a 17-season time series per unit for each variable. We used two prediction approaches: (i) optimal linear regression (OLR) whereby for each census unit the single predictor was selected that best explained the interannual zcNDVI variability, and (ii) a multi-layer feedforward neural network architecture, often called deep learning (DL), where all predictors for all units were combined in a single spatio-temporal model. Both approaches were evaluated with a leave-one-year-out cross-validation procedure. Both methods showed good prediction accuracies for small lead times and similar values for all lead times. The mean Rcv2 values for OLR were 0.95, 0.83, 0.68, 0.56, 0.46 and 0.37, against 0.96, 0.84, 0.65, 0.54, 0.46 and 0.38 for DL, for one, two, three, four, five, and six months lead time, respectively. Given the wide range of climates and vegetation types covered within the study area, we expect that the presented models can contribute to an improved early warning system for agricultural drought in different geographical settings around the globe.",
keywords = "Early-warning, Drought, Agriculture, Productivity, Prediction, Chile, MODIS, zcNDVI, Phenology, ITC-ISI-JOURNAL-ARTICLE",
author = "Francisco Zambrano and Anton Vrieling and Andy Nelson and Michele Meroni and Tsegaye Tadesse",
year = "2018",
month = "12",
day = "15",
doi = "10.1016/j.rse.2018.10.006",
language = "English",
volume = "219",
pages = "15--30",
journal = "Remote sensing of environment",
issn = "0034-4257",
publisher = "Elsevier",

}

Prediction of drought-induced reduction of agricultural productivity in Chile from MODIS, rainfall estimates, and climate oscillation indices. / Zambrano, Francisco (Corresponding Author); Vrieling, Anton; Nelson, Andy; Meroni, Michele; Tadesse, Tsegaye.

In: Remote sensing of environment, Vol. 219, 15.12.2018, p. 15-30.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Prediction of drought-induced reduction of agricultural productivity in Chile from MODIS, rainfall estimates, and climate oscillation indices

AU - Zambrano, Francisco

AU - Vrieling, Anton

AU - Nelson, Andy

AU - Meroni, Michele

AU - Tadesse, Tsegaye

PY - 2018/12/15

Y1 - 2018/12/15

N2 - Global food security is negatively affected by drought. Climate projections show that drought frequency and intensity may increase in different parts of the globe. These increases are particularly hazardous for developing countries. Early season forecasts on drought occurrence and severity could help to better mitigate the negative consequences of drought. The objective of this study was to assess if interannual variability in agricultural productivity in Chile can be accurately predicted from freely-available, near real-time data sources. As the response variable, we used the standard score of seasonal cumulative NDVI (zcNDVI), based on 2000–2017 data from Moderate Resolution Imaging Spectroradiometer (MODIS), as a proxy for anomalies of seasonal primary productivity. The predictions were performed with forecast lead times from one- to six-month before the end of the growing season, which varied between census units in Chile. Predictor variables included the zcNDVI obtained by cumulating NDVI from season start up to prediction time; standardised precipitation indices derived from satellite rainfall estimates, for time-scales of 1, 3, 6, 12 and 24 months; the Pacific Decadal Oscillation and the Multivariate ENSO oscillation indices; the length of the growing season, and latitude and longitude. For each of the 758 census units considered, the time series of the response and the predictor variables were averaged for agricultural areas resulting in a 17-season time series per unit for each variable. We used two prediction approaches: (i) optimal linear regression (OLR) whereby for each census unit the single predictor was selected that best explained the interannual zcNDVI variability, and (ii) a multi-layer feedforward neural network architecture, often called deep learning (DL), where all predictors for all units were combined in a single spatio-temporal model. Both approaches were evaluated with a leave-one-year-out cross-validation procedure. Both methods showed good prediction accuracies for small lead times and similar values for all lead times. The mean Rcv2 values for OLR were 0.95, 0.83, 0.68, 0.56, 0.46 and 0.37, against 0.96, 0.84, 0.65, 0.54, 0.46 and 0.38 for DL, for one, two, three, four, five, and six months lead time, respectively. Given the wide range of climates and vegetation types covered within the study area, we expect that the presented models can contribute to an improved early warning system for agricultural drought in different geographical settings around the globe.

AB - Global food security is negatively affected by drought. Climate projections show that drought frequency and intensity may increase in different parts of the globe. These increases are particularly hazardous for developing countries. Early season forecasts on drought occurrence and severity could help to better mitigate the negative consequences of drought. The objective of this study was to assess if interannual variability in agricultural productivity in Chile can be accurately predicted from freely-available, near real-time data sources. As the response variable, we used the standard score of seasonal cumulative NDVI (zcNDVI), based on 2000–2017 data from Moderate Resolution Imaging Spectroradiometer (MODIS), as a proxy for anomalies of seasonal primary productivity. The predictions were performed with forecast lead times from one- to six-month before the end of the growing season, which varied between census units in Chile. Predictor variables included the zcNDVI obtained by cumulating NDVI from season start up to prediction time; standardised precipitation indices derived from satellite rainfall estimates, for time-scales of 1, 3, 6, 12 and 24 months; the Pacific Decadal Oscillation and the Multivariate ENSO oscillation indices; the length of the growing season, and latitude and longitude. For each of the 758 census units considered, the time series of the response and the predictor variables were averaged for agricultural areas resulting in a 17-season time series per unit for each variable. We used two prediction approaches: (i) optimal linear regression (OLR) whereby for each census unit the single predictor was selected that best explained the interannual zcNDVI variability, and (ii) a multi-layer feedforward neural network architecture, often called deep learning (DL), where all predictors for all units were combined in a single spatio-temporal model. Both approaches were evaluated with a leave-one-year-out cross-validation procedure. Both methods showed good prediction accuracies for small lead times and similar values for all lead times. The mean Rcv2 values for OLR were 0.95, 0.83, 0.68, 0.56, 0.46 and 0.37, against 0.96, 0.84, 0.65, 0.54, 0.46 and 0.38 for DL, for one, two, three, four, five, and six months lead time, respectively. Given the wide range of climates and vegetation types covered within the study area, we expect that the presented models can contribute to an improved early warning system for agricultural drought in different geographical settings around the globe.

KW - Early-warning

KW - Drought

KW - Agriculture

KW - Productivity

KW - Prediction

KW - Chile

KW - MODIS

KW - zcNDVI

KW - Phenology

KW - ITC-ISI-JOURNAL-ARTICLE

UR - https://ezproxy2.utwente.nl/login?url=https://webapps.itc.utwente.nl/library/2018/isi/vrieling_pre.pdf

UR - https://ezproxy2.utwente.nl/login?url=https://doi.org/10.1016/j.rse.2018.10.006

U2 - 10.1016/j.rse.2018.10.006

DO - 10.1016/j.rse.2018.10.006

M3 - Article

VL - 219

SP - 15

EP - 30

JO - Remote sensing of environment

JF - Remote sensing of environment

SN - 0034-4257

ER -