# MS-YieldStackNet: multi-source data fusion for wheat yield estimation using a stacked ensemble neural network

## TL;DR

This paper introduces MS-YieldStackNet, a new AI model that combines satellite data, soil analysis, and weather to accurately predict wheat yields in Pakistan.

## Contribution

The novel MS-YieldStackNet framework fuses multi-source data using a stacked ensemble neural network for high-resolution wheat yield prediction.

## Key findings

- MS-YieldStackNet achieved an R-squared of 0.81 in wheat yield prediction.
- The model had an RMSE of 78.19 kg/ha and MAPE of 3.55%.
- The framework integrates multispectral imagery, soil data, and climate variables effectively.

## Abstract

Accurate crop yield prediction is vital for ensuring food security and informing agricultural policy, particularly in wheat-dependent regions like Pakistan where manual estimation methods are labor-intensive and imprecise. This study introduces a novel algorithmic framework, MS-YieldStackNet, to predict wheat yield with high spatial resolution by integrating multispectral satellite imagery, in-situ soil analytics, and meteorological variables. A unified feature space is constructed using Normalized Difference Vegetation Index (NDVI) and Difference Vegetation Index (DVI), soil physicochemical attributes, and temporal climate patterns, processed through a stacked ensemble neural architecture (MS-YieldStackNet) combining three parallel feed-forward neural networks (FFNNs) and a Random Forest meta-learner. The model achieved robust performance with an R-squared of 0.81, Mean Squared Error (MSE) of 6,114.30 kg/ha, root mean squared error (RMSE) of 78.19 kg/ha, mean absolute error (MAE) of 59.07 kg/ha, and mean absolute percentage error (MAPE) of 3.55%, demonstrating its potential for precise and scalable crop yield forecasting.