Climate, altitude, yield, and varieties drive lodging in sugarcane: A random forest approach to predict risk levels on a tropical island

Lodging is a critical factor in reducing sugarcane yields worldwide, mainly due to the selection of highly productive varieties. Understanding the response of yield and lodging to the combined effects of climate, sugarcane traits, and varieties has become a priority under climate change. The aim of this study was to better understand the influence of plant characteristics, climate, and soil conditions on the trade-off between sugarcane yield and lodging on the tropical Reunion Island. Data from a 14-year experimental network run by the eRcane breeding institute were used to build random-forest models to predict sugarcane yield and lodging classes, i.e. <10 %, 10–50 %, >50 % of lodging. Yield and lodging probability were then predicted across the island using climate change projections from 2015 to 2035. Both yield and lodging were highly influenced by the variety and characteristics (height and tillering) and climatic conditions. Areas on the island at high altitudes were subject to high probability of lodging (>50 %), while in areas with high wind speed, the risk of moderate lodging (10–50 %) increased. Overall, conditions or plant characteristics that favor higher yields increased lodging probability. Nevertheless, the correlation between yield and lodging probability varied considerably depending on the variety, highlighting the importance of sugarcane characteristics in resistance to lodging. This study highlights the fact that promoting more productive varieties in recent decades has led to an increase in lodging and identified critical environments on the island prone to increased risk of lodging. • Lodging and cane yield were predicted using random forest with a 14-year breeding dataset. • Lodging and cane yield were strongly influenced by plant height and tillering. • Lodging risk increased in areas at high altitudes or subject to high wind speed. • The trade-off between yield and lodging varied depending on the variety.

Authors

Institutions

Publication Details

Journal
European Journal of Agronomy
Published
2024-10-10
DOI
https://doi.org/10.1016/j.eja.2024.127381
Citations
2
Primary Topic
Sugarcane Cultivation and Processing
Type
article
Field-Weighted Citation Impact
1.20

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Climate, altitude, yield, and varieties drive lodging in sugarcane: A random forest approach to predict risk levels on a tropical island

Benjamin Heuclin, Mathilde Mellin, Raphaël Pilloni, Laurent Barau et al.
2 citations
European Journal of Agronomy
Sugarcane Cultivation and Processing
1.20
article

Climate, altitude, yield, and varieties drive lodging in sugarcane: A random forest approach to predict risk levels on a tropical island

Benjamin Heuclin, Mathilde Mellin, Raphaël Pilloni, Laurent Barau, Jean-Yves Hoarau, Mathias Christina, Thomas Dumont
article en
2 citations

Abstract

Lodging is a critical factor in reducing sugarcane yields worldwide, mainly due to the selection of highly productive varieties. Understanding the response of yield and lodging to the combined effects of climate, sugarcane traits, and varieties has become a priority under climate change. The aim of this study was to better understand the influence of plant characteristics, climate, and soil conditions on the trade-off between sugarcane yield and lodging on the tropical Reunion Island. Data from a 14-year experimental network run by the eRcane breeding institute were used to build random-forest models to predict sugarcane yield and lodging classes, i.e. <10 %, 10–50 %, >50 % of lodging. Yield and lodging probability were then predicted across the island using climate change projections from 2015 to 2035. Both yield and lodging were highly influenced by the variety and characteristics (height and tillering) and climatic conditions. Areas on the island at high altitudes were subject to high probability of lodging (>50 %), while in areas with high wind speed, the risk of moderate lodging (10–50 %) increased. Overall, conditions or plant characteristics that favor higher yields increased lodging probability. Nevertheless, the correlation between yield and lodging probability varied considerably depending on the variety, highlighting the importance of sugarcane characteristics in resistance to lodging. This study highlights the fact that promoting more productive varieties in recent decades has led to an increase in lodging and identified critical environments on the island prone to increased risk of lodging. • Lodging and cane yield were predicted using random forest with a 14-year breeding dataset. • Lodging and cane yield were strongly influenced by plant height and tillering. • Lodging risk increased in areas at high altitudes or subject to high wind speed. • The trade-off between yield and lodging varied depending on the variety.

European Journal of AgronomyVol. 161
Centre de Coopération Internationale en Recherche Agronomique pour le Développement (FR), Université de Montpellier (FR), Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement (FR), Conseil Régional de La Réunion (RE), Amélioration Génétique et Adaptation des Plantes méditerranéennes et tropicales (FR), Institut Agro Montpelier (FR), Services déconcentrés d'appui à la recherche Occitanie-Montpellier (FR), Agro-écologie et intensification durable des cultures annuelles
European Commission, Ministère de l'Agriculture et de l'Alimentation
Climate action
Openalex Percentile: Top 16%
Sugarcane Cultivation and Processing
1.20
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.