A Novel Robust Meta-Model Framework for Predicting Crop Yield Probability Distributions Using Multisource Data

Ermolieva, T., Havlik, P. ORCID: https://orcid.org/0000-0001-5551-5085, Derci Augustynczik, A.L., Boere, E., Frank, S. ORCID: https://orcid.org/0000-0001-5702-8547, Kahil, T. ORCID: https://orcid.org/0000-0002-7812-5271, Wang, G., Balkovič, J. ORCID: https://orcid.org/0000-0003-2955-4931, Skalský, R. ORCID: https://orcid.org/0000-0002-0983-6897, Folberth, C. ORCID: https://orcid.org/0000-0002-6738-5238, Komendantova, N. ORCID: https://orcid.org/0000-0003-2568-6179, & Knopov, P. S. (2023). A Novel Robust Meta-Model Framework for Predicting Crop Yield Probability Distributions Using Multisource Data. Cybernetics and Systems Analysis 10.1007/s10559-023-00620-z.

Full text not available from this repository.
Project: GLOBIOM

Abstract

There is an urgent need to better understand and predict crop yield responses to weather disturbances, in particular, of extreme nature, such as heavy precipitation events, droughts, and heat waves, to improve future crop production projections under weather variability, extreme events, and climate change. In this paper, we develop quantile regression models for estimating crop yield probability distributions depending on monthly temperature and precipitation values and soil quality characteristics, which can be made available for different climate change projections. Crop yields, historical and those simulated by the EPIC model, are analyzed and distinguished according to their levels, i.e., mean and critical quantiles. Then, the crop yield quantiles are approximated by fitting separate quantile-based regression models. The developed statistical crop yield meta-model enables the analysis of crop yields and respective probabilities of their occurrence as a function of the exogenous parameters such as temperature and precipitation and endogenous, in general, decision-dependent parameters (such as soil characteristics), which can be altered by land use practices. Statistical and machine learning models can be used as reduced form scenario generators (meta-models) of stochastic events (scenarios), as a submodel of more complex models, e.g., Integrated Assessment model (IAM) GLOBIOM.

Item Type: Article
Uncontrolled Keywords: extreme events, climate change, food security, crop yields projections, probability distributions, quantile regressions, robust estimation and machine learning, two-stage STO
Research Programs: Advancing Systems Analysis (ASA)
Advancing Systems Analysis (ASA) > Cooperation and Transformative Governance (CAT)
Biodiversity and Natural Resources (BNR)
Biodiversity and Natural Resources (BNR) > Agriculture, Forestry, and Ecosystem Services (AFE)
Biodiversity and Natural Resources (BNR) > Integrated Biosphere Futures (IBF)
Biodiversity and Natural Resources (BNR) > Water Security (WAT)
Depositing User: Luke Kirwan
Date Deposited: 10 Oct 2023 10:14
Last Modified: 10 Oct 2023 10:14
URI: https://pure.iiasa.ac.at/19127

Actions (login required)

View Item View Item