# Soil Texture Classification with 1D Convolutional Neural Networks based on Hyperspectral Data

## TL;DR

This study develops and compares five 1D CNN models for soil texture classification using hyperspectral data, demonstrating that the shallowest model with coordinate layers achieves the highest accuracy on the LUCAS dataset.

## Contribution

Introduces three novel 1D CNN architectures for soil texture classification and compares them with existing approaches using hyperspectral data.

## Key findings

- LucasCoordConv achieves the highest average accuracy.
- Shallower CNN models outperform deeper ones.
- CNN approaches outperform random forest classifiers.

## Abstract

Soil texture is important for many environmental processes. In this paper, we study the classification of soil texture based on hyperspectral data. We develop and implement three 1-dimensional (1D) convolutional neural networks (CNN): the LucasCNN, the LucasResNet which contains an identity block as residual network, and the LucasCoordConv with an additional coordinates layer. Furthermore, we modify two existing 1D CNN approaches for the presented classification task. The code of all five CNN approaches is available on GitHub (Riese, 2019). We evaluate the performance of the CNN approaches and compare them to a random forest classifier. Thereby, we rely on the freely available LUCAS topsoil dataset. The CNN approach with the least depth turns out to be the best performing classifier. The LucasCoordConv achieves the best performance regarding the average accuracy. In future work, we can further enhance the introduced LucasCNN, LucasResNet and LucasCoordConv and include additional variables of the rich LUCAS dataset.