A hybrid deep learning framework for estimating urban tree transpiration

Q: What does this research mean for the field?

A hybrid deep learning framework can accurately estimate urban tree transpiration with limited training data while identifying species-specific response patterns that align with known hydraulic architecture differences. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.SUPPORTS_CONSENSUS.

Xiang Zhang; Xue Zhong; Jun-Ru Yan; Qi Li; Kai-Xin Liu; Lingye Yao; Longhao Zhang; Astrid Moser-Reischl; Thomas Rötzer; Stephan Pauleit; Mohammad A. Rahman

doi:10.1016/j.jenvman.2026.130780

August 28, 2026Journal of Environmental ManagementOpen Access

A hybrid deep learning framework for estimating urban tree transpiration

View Full Paper

Ask AI

Bookmark

Share

Key Points

To develop and evaluate a hybrid deep learning framework capable of estimating urban tree transpiration under limited training data while integrating process-based physiological mechanisms.
Trained a hybrid deep learning model using transpiration and environmental data across two urban tree species under limited-data constraints.
Applied SHAP (Shapley Additive explanations) interpretability techniques to evaluate model-derived response patterns against physiological hydraulic architecture and identify domains of Jarvis model failure.
Achieved high predictive accuracy for transpiration across two distinct tree species while maintaining robust performance under limited training data.
Identified species-specific environmental response patterns matching hydraulic architecture differences and isolated specific regimes where empirical Jarvis model assumptions underperform.

Ask about this paper

Answers are grounded in this paper and cite their sources.

Implication

Modeling study demonstrates accurate urban tree transpiration estimation across two species, suggesting practical integration into urban microclimate models.

Abstract

for two species, while maintaining strong performance with limited training data. SHAP identifies model-derived species-specific response patterns consistent with known differences in hydraulic architecture, and diagnoses regimes where Jarvis assumptions underperform. This framework offers a practical pathway for embedding process knowledge into broader urban evapotranspiration and microclimate models.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/6a93f07a6c1a8fb52e79cad9 https://doi.org/10.1016/j.jenvman.2026.130780

View Full Paper

Ask AI

Bookmark

Share

A hybrid deep learning framework for estimating urban tree transpiration

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

A hybrid deep learning framework for estimating urban tree transpiration

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading