A Hybrid Computational Intelligence Framework Integrating

XGBoost and Residual Neural Networks for Multi-Crop Yield

Prediction

Yasser H. Elawady1,*

1Department of Artificial Intelligence, College of AI and Information, Horus University, Egypt

Received: March 09, 2026 Revised: May 14, 2026 Accepted: July 14, 2026 ⋆ Corresponding author

ABSTRACT

Reliable crop-yield prediction is essential for strategic food planning, input allocation, and precision-agriculture

analytics, yet a single predictive model must accommodate substantial heterogeneity across crop species, regions,

seasons, and management conditions. This paper proposes a hybrid computational-intelligence framework that

couples extreme gradient boosting with an ensemble of residual neural networks in order to model both dominant

nonlinear structure and systematic residual error. A leakage-controlled benchmark was constructed from a recent

public agricultural data release, yielding 2,698 observations spanning eight major crops, 30 Indian states and union

territories, six agricultural seasons, and ten complete years from 2010 to 2019. The predictor space combines climatic

and agronomic descriptors, including annual rainfall, cultivated area, fertilizer and pesticide intensities, crop identity,

state, season, temporal trend, and rainfall–management interaction terms; the production variable was removed to

prevent algebraic target leakage. The empirical study compares the proposed framework with nine competitive

baselines under a strict chronological design in which 2010–2017 are used for training, 2018 for model selection, and

2019 for independent testing. On the holdout year, the proposed hybrid attains R2 = 0.974, RMSE = 3.146 t ha−1,

and MAE = 1.080 t ha−1, outperforming standalone XGBoost by 20.3% in RMSE and a direct deep neural network

by 32.5%. Bootstrap analysis places the hybrid RMSE within 2.042–4.112 t ha−1 at the 95% confidence level.

Grouped permutation analysis shows that crop identity, geographic location, and cultivated area contribute most

strongly to predictive performance. Overall, the results support residual error correction as an effective strategy for

strengthening tabular yield prediction while also underscoring the importance of leakage control, temporal validation,

and competitive baseline design.

Keywords: Crop yield prediction Computational intelligence Extreme gradient boosting Deep neural networks

Residual learning Precision agriculture Ensemble learning

1. INTRODUCTION

Crop yield estimates influence food-security assessment, market

planning, insurance, irrigation, fertilizer allocation, and

public policy. Their estimation is nevertheless challenging

because the response arises from interactions among climate,

soil, crop genetics, management practices, geography, and

time. Machine-learning models can represent nonlinearities

that are difficult to prescribe analytically, but their apparent

accuracy is sensitive to data leakage, random rather than temporal

validation, limited crop diversity, and weak baselines

[1, 2, 3, 4].

Recent studies have demonstrated the value of convolutional,

recurrent, boosted-tree, and ensemble architectures for re-