Lightweight Near-Infrared Spectral Reconstruction from Red UAV Imagery Using Artificial Intelligence for Low-Cost Remote Sensing
Open Access
- 4 September 2026
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 18 (17) , 3015
Abstract
Near-infrared imagery is essential for vegetation monitoring, precision agriculture, and environmental remote sensing, but multispectral UAV systems remain significantly more expensive and less accessible than conventional RGB imaging platforms. This study presents a lightweight artificial intelligence framework for reconstructing the NIR spectral band exclusively from the red spectral band acquired by a UAV. The proposed methodology formulates the reconstruction task as a pixel-wise nonlinear regression problem and employs a compact multilayer perceptron (MLP) containing only 609 trainable parameters, without exploiting spatial neighborhood information. The framework was developed and evaluated using 280 synchronized multispectral UAV image sets acquired with a DJI Phantom 4 Multispectral platform over a heterogeneous agricultural landscape in the Republic of Moldova. Of these, 252 image sets were used for model development, and 28 were reserved as a held-out within-mission test subset. Quantitative evaluation on a held-out test dataset from the same acquisition mission yielded a mean squared error of 0.010329, a root mean squared error of 0.101632, a mean absolute error of 0.079883, a coefficient of determination of 0.253383, and a Pearson correlation coefficient of 0.683637 between measured and reconstructed normalized NIR digital intensities. The results indicate that the model captures part of the red–NIR relationship under the evaluated acquisition conditions; however, the moderate coefficient of determination suggests that the reconstructed values are an approximation rather than a replacement for measured NIR observations. An illustrative NDVI-based assessment showed that broad spatial vegetation patterns remained identifiable. Rather than introducing a new neural network architecture, this work establishes a compact empirical baseline to investigate the practical performance and limitations of pixel-wise NIR reconstruction from a single red-band value with minimal model complexity.Keywords
Funding Information
- Scientific Research Excellence Stimulation Project (25.80012.5007.71SE)
This publication has 28 references indexed in Scilit:
- Assessment of light environment conditions for reconstruction of multispectral images by conditional adversarial networksBiosystems Engineering, 2025
- Multifiltering MLP for Spectral Super-Resolution With Remote Sensing Image VerificationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024
- Empirical curvelet transform based deep DenseNet model to predict NDVI using RGB drone imagery dataComputers and Electronics in Agriculture, 2024
- An open-source machine-learning application for predicting pixel-to-pixel NDVI regression from RGB calibrated imagesComputers and Electronics in Agriculture, 2023
- Cost-efficient coupled learning methods for recovering near-infrared information from RGB signals: Application in precision agricultureComputers and Electronics in Agriculture, 2023
- NDVI/NDRE prediction from standard RGB aerial imagery using deep learningComputers and Electronics in Agriculture, 2022
- Deep convolutional neural network for damaged vegetation segmentation from RGB images based on virtual NIR-channel estimationArtificial Intelligence in Agriculture, 2022
- Perspectives for Remote Sensing with Unmanned Aerial Vehicles in Precision AgricultureTrends in Plant Science, 2019
- Characterization of Sentinel-2A and Landsat-8 top of atmosphere, surface, and nadir BRDF adjusted reflectance and NDVI differencesRemote Sensing of Environment, 2018
- Red and photographic infrared linear combinations for monitoring vegetationRemote Sensing of Environment, 1979