Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Seasonal Pre-planting Drought Impact-based Forecasting of Crop Yield in India
Uppsala University, Disciplinary Domain of Science and Technology, Earth Sciences, Department of Earth Sciences, Air, Water and Landscape Sciences. Ctr Nat Hazards & Disaster Sci CNDS, Uppsala, Sweden.ORCID iD: 0000-0002-0492-7407
Universita degli Studi di Trento Dipartimento di Ingegneria Civile Ambientale e Meccanica.
Uppsala University, Disciplinary Domain of Science and Technology, Earth Sciences, Department of Earth Sciences, Air, Water and Landscape Sciences.ORCID iD: 0000-0001-5350-2934
European Centre for Medium-Range Weather Forecasts.
Show others and affiliations
2026 (English)In: Earth's Future, E-ISSN 2328-4277, Vol. 14, no 4, article id e2025EF007128Article in journal (Refereed) Published
Abstract [en]

Accurate drought impact-based forecasting of crop yield in India remains challenging due to the country’s hydro-climatic diversity and complex interactions between climate variability, ecosystem vulnerability, and agriculture. This study develops a framework integrating observed and forecasted drought indices across multiple accumulation periods to predict standardised crop yields at seasonal lead time before planting. Using district-level and cluster-based approaches, we apply Random Forest, Extreme Gradient Boosting, and Artificial Neural Networks to establish indicator–impact relationships for paddy rice (wet season) and wheat (dry season), leveraging historical yield data and seasonal forecasts.

District-level models outperform cluster-based ones, with Random Forest showing the best performance. Over 80% of wheat districts and 70% of rice districts achieve strong predictive accuracy, defined as RMSE below 0.2 in the test set. Incorporating ECMWF’s SEAS5 forecasts enables reliable rice yield predictions up to six months before the season—covering over 80% of wheat districts and 60–70% of rice districts. Forecast skill assessed using Continuous Ranked Probability Score (CRPS) confirms robustness across space and time, especially in districts with moderate yield variability. Weighted CRPS shows forecasts for extremely low yields (below the 10th percentile) are accurate and reliable—crucial for early warning and preparedness.

This work advances operational impact-based drought forecasting in India, offering a tool to inform anticipatory action among farmers, water managers, and supply chains. By linking drought observations and seasonal forecasts to crop yield outcomes, the study provides a replicable early warning approach to support targeted mitigation and enhance climate resilience in agriculture.

Place, publisher, year, edition, pages
American Geophysical Union (AGU), 2026. Vol. 14, no 4, article id e2025EF007128
National Category
Environmental Sciences
Identifiers
URN: urn:nbn:se:uu:diva-564239DOI: 10.1029/2025EF007128ISI: 001740652300001OAI: oai:DiVA.org:uu-564239DiVA, id: diva2:1986269
Part of project
En avancerad databas av effekterna av extrema klimathändelser i Europa från nättexter, Swedish Research CouncilCentre of excellence on Impacts of Climate Extremes under global change (ICE), Swedish Research Council
Funder
EU, Horizon 2020, 956396EU, European Research Council, 101112727EU, European Research Council, 101137601EU, Horizon 2020, 101037293EU, Horizon 2020, 101003876EU, Horizon Europe, 101121192EU, European Research Council, 948309Available from: 2025-07-30 Created: 2025-07-30 Last updated: 2026-04-29Bibliographically approved
In thesis
1. On seasonal predictability of droughts and their impacts: Bridging science and operational applications
Open this publication in new window or tab >>On seasonal predictability of droughts and their impacts: Bridging science and operational applications
2025 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Droughts are among the most complex and least understood natural hazards, with impacts that are often delayed, diffuse, and deeply context-dependent. Despite advances in hydro-meteorological forecasting, a persistent gap remains between the detection of drought conditions and the anticipation of their societal consequences. This thesis addresses this gap by advancing the science and operational potential of impact-based forecasting for droughts.

This work combined conceptual synthesis, statistical analysis, and machine learning to explore the relationships between drought indicators and sector-specific impacts across Europe and India. First, a structured overview of the current state of the art and practical challenges is provided. Then, drought indicators are related to observed impacts to assess their predictability across Europe using seasonal forecasts. Lastly, a pre-season forecasting framework for crop yield in India is developed and evaluated to explore the feasibility of anticipatory impact prediction at district level.

The findings show that indicator–impact relationships are highly variable across space, time, and sectors, and that even modest improvements in forecast skill can yield meaningful benefits for early action. By integrating seasonal forecasts with impact-relevant indicators, this thesis contributes to the development of more actionable, context-specific early warning systems. It also highlights the need for co-produced, user-centred approaches that bridge the gap between climate signals and real-world decisions.

Place, publisher, year, edition, pages
Uppsala: Acta Universitatis Upsaliensis, 2025. p. 69
Series
Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology, ISSN 1651-6214 ; 2560
Keywords
drought, natural hazards, hydrological risk, climate change, extreme weather, drought indicators, early warning systems, drought impacts, seasonal forecasting
National Category
Environmental Sciences
Research subject
Earth Science with specialization in Environmental Analysis
Identifiers
urn:nbn:se:uu:diva-564240 (URN)978-91-513-2538-5 (ISBN)
Public defence
2025-09-26, Hambergsalen, Uppsala, 10:00 (English)
Opponent
Supervisors
Available from: 2025-09-02 Created: 2025-07-30 Last updated: 2025-09-02

Open Access in DiVA

fulltext(8594 kB)235 downloads
File information
File name FULLTEXT02.pdfFile size 8594 kBChecksum SHA-512
b660f2530268ed5afd846743f97d8ccab544366c4942566a4c364af9210399070bd4682190e0538d3e17007c100d60aa6ca585e35e524e89a22e4e1f8d581994
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Shyrokaya, AnastasiyaSamantaray, AlokDi Baldassarre, GiulianoMessori, Gabriele
By organisation
Air, Water and Landscape Sciences
In the same journal
Earth's Future
Environmental Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 235 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 213 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf