Remote sensing data imputation using deep learning for multispectral imagery
Quick Take
Deep learning models, including CNN and CNN-LSTM architectures, significantly outperform traditional linear interpolation for imputing missing spectral bands in multispectral imagery, enhancing algal bloom monitoring in lakes. The study shows CNN achieved the best performance across multiple lakes, improving the reliability of water monitoring applications.
Key Points
- Deep learning models outperformed linear interpolation in spectral band imputation.
- CNN architecture delivered the best performance across most lakes studied.
- Improved data completeness enhances monitoring of critical events like algal blooms.
- Study focused on PlanetScope SuperDove imagery for water monitoring applications.
- Algal bloom indices derived from imputed data matched observed data closely.
Article Content
From source RSS / original summaryarXiv:2605. 24003v1 Announce Type: new Abstract: Remote sensing techniques have been increasingly utilised in aquatic applications in recent years. A common challenge in using optical satellite data is the presence of missing observations due to cloud cover. These data gaps can lead to missed detection of critical events, such as algal blooms, in lakes of high interest to water authorities.
As a result, enhancing the completeness of optical satellite datasets is crucial for improving the monitoring and prediction of algal blooms. In this study, we compared a traditional data imputation method (i. e. , linear interpolation) with deep learning models for reconstructing missing spectral bands across four lakes with historical records of algal blooms. The deep learning models adopted include CNN-based architectures (i. e. , CNN, Inception Resnet, and Autoencoder) and CNN-LSTM-based architectures (i. e.
, CNN-LSTM, Resnet-LSTM, and Autoencoder-LSTM). Our results demonstrated that deep learning models substantially outperformed the baseline linear interpolation method in imputing spectral band values within artificially masked regions. Among these models, CNN delivered the best performance across most lakes. Furthermore, we evaluated the performance of algal bloom indices (i. e. , Green/Red and NDCI) derived from the imputed imagery by comparing them with the observed data.
Our results demonstrate that deep learning models are effective for imputing missing data in PlanetScope SuperDove imagery, enabling more reliable applications in water monitoring.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential Tuning
Evi-Steer introduces a novel evidential tuning framework for BiomedCLIP, achieving 0.11% parameter updates while enhancing uncertainty-aware fine-tuning. It outperforms state-of-the-art methods across 15 biomedical imaging datasets, proving effective in few-shot learning and domain shifts for clinical applications.