Efraín Alberto Padilla-Zepeda

Dr. Efraín Alberto Padilla-Zepeda

Imaging Spectroscopy Department, German Aerospace Center (DLR), Weßling, Germany
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Efraín Alberto Padilla-ZepedaEfraín Alberto Padilla-Zepeda
Efraín Alberto Padilla-Zepeda
DTDeni Librado Torres-Roman
Deni Librado Torres-Roman
AMAndres Mendez-Vazquez
Andres Mendez-Vazquez
The present work, unlike others, does not try to reduce the noise in hyperspectral images to increase the semantic segmentation performance metrics; rather, we present a classification framework for noisy Hyperspectral Images (HSI), studying the classification performance metrics for different SNR levels and where the inputs are compressed. This framework consists of a 3D Convolutional Neural Network (3DCNN) that uses as input data a spectrally compressed version of the HSI, obtained from the Tucker Decomposition (TKD). The advantage of this classifier is the ability to handle spatial and spectral features from the core tensor, exploiting the spatial correlation of remotely sensed images of the earth surface. To test the performance of this framework, signal-independent thermal noise and signal-dependent photonic noise generators are implemented to simulate an extensive collection of tests, from 60 dB to −20 dB of Signal-to-Noise Ratio (SNR) over three datasets: Indian Pines (IP), University of Pavia (UP), and Salinas (SAL). For comparison purposes, we have included tests with Support Vector Machine (SVM), Random Forest (RF), 1DCNN, and 2DCNN. For the test cases, the datasets were compressed to only 40 tensor bands for a relative reconstruction error less than 1%. This framework allows us to classify the noisy data with better accuracy and significantly reduces the computational complexity of the Deep Learning (DL) model. The framework exhibits an excellent performance from 60 dB to 0 dB of SNR for 2DCNN and 3DCNN, achieving a Kappa coefficient from 0.90 to 1.0 in all the noisy data scenarios for a representative set of labeled samples of each class for training, from 5% to 10% for the datasets used in this work. The source code and log files of the experiments used for this paper are publicly available for research purposes.

30 June 2020 in ECORFAN Journal Bolivia
Verified
Journal Article
Open access
Efraín Alberto Padilla-ZepedaEfraín Alberto Padilla-Zepeda
Efraín Alberto Padilla-Zepeda
DTDeni Librado Torres-Roman
Deni Librado Torres-Roman
AMAndrés Mendez-Vazquez
Andrés Mendez-Vazquez
Given the improvement of Remote Sensing (RS) sensors, it has been possible to increase spatial and spectral resolution on many of them. Nevertheless, the amount of data to represent and post-process has become highly prohibitive. Therefore, the need to be able to process such huge data sets, and one of the possible ways to deal with problems is the use of compression methods, however, data loss happen if the need of data size reduction is a must. RS spectral imagery contain high quantities of redundant information along the spectral domain, thus, making possible to use compression methods effectively as for example, tensor decomposition algorithms. In Tucker decomposition (TKD), an interesting and strange phenomenon happens when spatial domain is maintained and spectral domain is reduced, as a preprocessing step of a semantic segmentation task. Under these conditions, it is possible to observe an improvement on Pixel Accuracy (PA) metric when it is compared with the same uncompressed spectral image. Therefore, this work presents a study on how noise affects the Tucker Decomposition compared with Principal Component Analysis (PCA) and its impact in semantic segmentation.

19 June 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
Efraín Alberto Padilla-ZepedaEfraín Alberto Padilla-Zepeda
Efraín Alberto Padilla-Zepeda
KAKevin Alonso
Kevin Alonso
RRRaquel De Los Reyes
Raquel De Los Reyes
DTDeni Librado Torres-Roman
Deni Librado Torres-Roman
APAvi Putri Pertiwi
Avi Putri Pertiwi
TSTobias Storch
Tobias Storch
This paper presents a method to improve pixel-level classification of Sentinel-2 imagery by integrating spectral index-based masking with deep learning approaches using 1D, 2D, and 3D Convolutional Neural Networks (CNN1D, CNN2D, and CNN3D). Rather than relying on manually labeled data, the proposed method selects high-quality training samples from PACO (Python-based Atmospheric COrrection software), using pixel selection strategies to remove ambiguous or inconsistent labels. Three selection strategies are explored: full inclusion, uniqueness-based filtering, and physics-based rules. Unlike traditional masking algorithms based only on spectral indices, the CNN models leverage spatial correlations among neighboring pixels across all spectral bands, plus auxiliary features like elevation and illumination, enabling the extraction of more informative representations and improved classification accuracy, particularly in complex scenes. The model is trained using a large global training dataset from PACO, while a separate validation dataset from the same source is used to monitor performance during learning and prevent overfitting. Final evaluation is performed using two independent manually labeled testing datasets (TD1 and TD2) that span diverse land cover types and atmospheric conditions. Compared to PACO's baseline classification, our CNN approaches achieve consistent improvements for normalized Matthews Correlation Coefficient (nMCC), with maximum gains of +3.3 percentage points (pp) on TD1 (from 0.855 to 0.888) and +18.3pp on TD2 (from 0.665 to 0.848). The largest class- wise gains are observed for shadows and clear land-related classes, with up to +22.7pp improvement. These results confirm the effectiveness of the proposed training strategy and its potential for improving label quality in large-scale Earth observation pipelines.