Sociohydrological model structure deficiency assessment and hybrid model selection.
Saved in:
| Title: | Sociohydrological model structure deficiency assessment and hybrid model selection. |
|---|---|
| Authors: | Djohan, Dennis1 (AUTHOR), Malard-Adam, Julien2,3,4 (AUTHOR), Adla, Soham1 (AUTHOR), Pande, Saket1 (AUTHOR) s.pande@tudelft.nl |
| Source: | Journal of Hydrology. Feb2026, Vol. 666, pN.PAG-N.PAG. 1p. |
| Subjects: | Irrigation management, Machine learning, Integrated water development, Design failures, Agrarian societies, Agricultural forecasts, Model validation, Statistical models |
| Geographic Terms: | India |
| Abstract: | Sociohydrology aims to deliver user-inspired solutions to water challenges, often through model-based understanding and simulation of local realities. However, sociohydrological modeling methodologies used to understand such complex human-water systems remain difficult to apply to many real-world case studies. Sociohydrological model predictions at daily to annual time scales of decision- making remain a challenge due to often difficult-to-acquire social sciences data, and missing or unknown feedbacks that lead to model structural errors, among other issues. This paper assesses and reduces model structural deficiencies of a smallholder sociohydrological (SH) model when applied to a case study of small-scale agricultural production in India, where variables from a farmer survey help alleviate structural deficiencies. A structural error model is proposed based on a regression model of nonlinear projection of the these variables to a Kernel space, called Kernel Principal Component Analysis (KPCA) based model. Based on this, a hybrid model that is a sum of the SH model and the structural error model is proposed. It offers significantly better yield predictions on 'unseen' (to the model) survey data than the SH only model. The hybrid model also performs better on yield prediction than a KPCA model alone, which predicts yields without any SH dynamics. This is because the hybrid model combines the structural error model that learns from the spatial pattern of observed yields with the temporal dynamics explained by the SH model alone. The results indicate that the structure of the SH model can be improved by further incorporation of irrigation and adaptive behaviour of farmers. • Farm survey identifies sociohydrological (SH) model deficiencies in yield predictions. • Mixed method of surveys and machine learning used to model SH structural errors. • Hybrid SH model predicts better than SH only and machine learning only models. • Structural errors arise due to absence of irrigation practices and farmer adaptations. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Hydrology is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
Be the first to leave a comment!
