Turning spectra into images improves plant trait retrieval with 2D-CNNs
2026-08-17 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionMachine Learning
AI summaryⓘ
The authors explored whether turning 1D leaf spectra data into 2D images can help better predict plant traits using deep learning. They found that simply reshaping the spectrum into a 2D grid and using a convolutional neural network improved predictions compared to traditional 1D methods. Pretraining on many unlabeled spectral images also helped but did not outperform all 1D methods in new data tests. By analyzing which wavelengths influenced predictions, the authors found agreement with known leaf chemistry for some traits but not others. Overall, the improvement came mainly from representing spectra as 2D images rather than more complex models or pretraining.
Hyperspectral reflectance spectroscopyPlant functional traitsConvolutional neural networks (CNN)1D vs 2D spectral representationEfficientNet-B0Masked autoencoder (MAE)Integrated GradientsGrad-CAMPROSAIL modelSelf-supervised learning
Authors
Javier Lopatin, Teja Kattenborn, Eya Cherif, Sebastián Moreno
Abstract
Hyperspectral reflectance spectroscopy enables non-destructive estimation of plant functional traits, yet current deep learning approaches process spectra as one-dimensional sequences, which limits how they capture long-range inter-band dependencies. We asked whether transforming 1D spectra into 2D image representations improves multi-trait prediction with convolutional neural networks (CNN). We compared nine transformations using EfficientNet-B0 on the GreenHyperSpectra dataset (7,897 labeled spectra, eight traits, 400-2450 nm), benchmarked against published 1D CNN results on the same split. Trained from scratch, the simplest transformation, a direct Reshape of the spectrum into a 2D grid, performed best ($R^2 = 0.684 \pm 0.001$) and improved on the state-of-the-art 1D baseline ($R^2 = 0.587$, $+0.097$). We then pretrained a 2D masked autoencoder (MAE-2D) on 139,000 unlabeled spectral images. Linear probing, which freezes the encoder and trains only a multilayer perceptron head, reached $R^2 = 0.646$ and exceeded every 1D self-supervised counterpart, including the fine-tuned MAE-1D ($R^2 = 0.641$). Under cross-dataset evaluation all models lost most of their accuracy and none beat the 1D baseline significantly. To identify which wavelengths drive each prediction, we applied Integrated Gradients and Grad-CAM and unfolded band importance back to the spectral axis. Protein ($r = 0.45$) and leaf water ($r = 0.33$) agreed with sensitivities simulated by the PROSAIL radiative-transfer model, while carotenoids ($r = 0.06$) and leaf area index ($r = -0.11$) did not, showing that the model reads established leaf chemistry for traits with sharp absorption features. The representational advantage of 2D spectral images, rather than architectural complexity or ImageNet pretraining, drives the gain over 1D approaches.