# Enhanced Cropland SOM Prediction via LEW-DWT Fusion of Multi-Temporal Landsat 8 Images and Time-Series NDVI Features

## TL;DR

This study improves soil organic matter prediction in croplands using a new image fusion method and machine learning models.

## Contribution

The novel LEW-DWT fusion method enhances spatial detail preservation for better SOM prediction.

## Key findings

- LEW-DWT fusion achieved the lowest spectral distortion and highest spatial fidelity for cropland images.
- CNN models using Ev–Tn–Mm features outperformed RF models with an R2 of 0.62.
- Soil moisture-related variables were the most important for SOM prediction, contributing 45.84% of total importance.

## Abstract

Soil organic matter (SOM) is a key indicator of arable land quality and the global carbon cycle; accurate regional-scale SOM estimation is vitally significant for sustainable agricultural development and climate change research. This study evaluates a multisource data-fusion approach for improving cropland SOM prediction in Yucheng City, Shandong Province, China. We applied a Local Energy Weighted Discrete Wavelet Transform (LEW-DWT) to fuse multi-temporal Landsat 8 imagery (2014–2023). Quantitative analysis (e.g., Information Entropy and Average Gradient) demonstrated that LEW-DWT effectively preserved high-frequency spatial details and texture features of fragmented croplands better than traditional DWT and simple splicing methods. These were combined with 41 environmental predictors to construct composite Ev–Tn–Mm features (environmental variables, temporal NDVI features, and multi-temporal multispectral information). Random Forest (RF) and Convolutional Neural Network (CNN) models were trained and compared to assess the contribution of the fused data to SOM mapping. Key findings are: (1) Comparative analysis showed that the LEW-DWT fusion strategy achieved the lowest spectral distortion and highest spatial fidelity. Using the fused multitemporal dataset, the CNN attained the highest predictive performance for SOM (R2 = 0.49). (2) Using the Ev–Tn–Mm features, the CNN achieved R2 = 0.62, outperforming the RF model (R2 = 0.53). Despite the limited sample size, the optimized shallow CNN architecture effectively extracted local spatial features while mitigating overfitting. (3) Variable importance analysis based on the RF model reveals that mean soil moisture is the primary single variable influencing the SOM, (relative importance 15.22%), with the NDVI phase among time-series features (1.80%) and the SWIR1 band among fused multispectral bands (1.38%). (4) By category, soil moisture-related variables contributed 45.84% of total importance, followed by climatic factors. The proposed multisource fusion framework offers a practical solution for regional SOM digital monitoring and can support precision agriculture and soil carbon management.