EmissionNet: Air Quality Pollution Forecasting for Agriculture

TL;DR

This paper introduces EmissionNet and EmissionNet-Transformer, two deep learning models that improve air quality pollution forecasting for agriculture by capturing complex spatial-temporal dependencies in emissions data.

Contribution

The paper proposes two novel deep learning architectures, EmissionNet and EmissionNet-Transformer, tailored for forecasting agricultural N₂O emissions, addressing limitations of traditional physics-based models.

Findings

EmissionNet outperforms baseline models in accuracy.

Transformer-based architecture captures complex dependencies effectively.

Models demonstrate potential for improved environmental monitoring.

Abstract

Air pollution from agricultural emissions is a significant yet often overlooked contributor to environmental and public health challenges. Traditional air quality forecasting models rely on physics-based approaches, which struggle to capture complex, nonlinear pollutant interactions. In this work, we explore forecasting N$_2$O agricultural emissions through evaluating popular architectures, and proposing two novel deep learning architectures, EmissionNet (ENV) and EmissionNet-Transformer (ENT). These models leverage convolutional and transformer-based architectures to extract spatial-temporal dependencies from high-resolution emissions data