--- title: >- Satellite extractor: Towards a Smart Eco-epidemiological Model of Dengue in Colombia using Satellite Imagery*. emoji: 🌍 colorFrom: yellow colorTo: green sdk: static pinned: false --- # Sentinelhub grant: Sponsoring request ID 1c081a - Towards a Smart Eco-epidemiological Model of Dengue in Colombia using Satellite in Collaboration with MIT Critical Data Colombia. Project supported by ESA Network of Resources Initiative These datasets have been extracted using [satellite extractor](https://github.com/sebasmos/satellite.extractor) and the metadata using [Metadengue](https://github.com/sebasmos/MetaDengue) **Project Organisation**: MIT Critical Data Colombia. ## Model Description - **Repository:** [Code](https://github.com/sebasmos/satellite.extractor) - **ESA project:** Sponsoring request ID 1c081a - Towards a Smart Eco-epidemiological Model of Dengue in Colombia using Satellite in Collaboration with MIT Critical Data Colombia) - **Point of Contact:** [Sebastian A. Cajas Ordóñez](mailto:scajasordonez@gmail.com) ## Summary Here below find all the dataset's versions and descriptions. *Baseline method from satellite extractor*: Raw data from Sentinel 2LC1 with recursive artifact removal, clouds removal based on LeastCC and Nearest Interpolation for spatial resolution. * **SAT1_dataset_5_best_cities**: Top 5 municipalities based on Baseline method from satellite extractor * **SAT2_dataset_10_best_cities**: Top 10 municipalities based on Baseline method from satellite extractor * **SAT3_FULL_COLOMBIA**: Top 81 municipalities based on Baseline method from satellite extractor * **SAT4_dataset_10_best_cities_augmented_v1**: Augmented data with aligned metadata. Data was extracted using recursive artifact removal, cloud removal based on LeastCC, and Nearest Interpolation for spatial resolution. Implemented [here](https://github.com/sebasmos/satellite.extractor/blob/main/notebooks/satellite_imagery_augmentation.ipynb) and augmentations applied to RGB channels while leaving other satellite channels unchanged: *Pre-processing*: The first step is to apply Contrast Limited Adaptive Histogram Equalization (CLAHE) to the image, with a clip limit of 6.0 and a tile grid size of 16 by 16. This technique enhances the contrast of the image while preventing over-amplification of noise. Secondly, we apply the RGBShift augmentation technique, which randomly shifts the values of pixels in the red, green, and blue channels of the image. This is done with a probability of 100% and is applied to 30 pixels per channel. Finally, we apply the RandomBrightnessContrast augmentation technique with a probability of 50%. This technique randomly adjusts the brightness and contrast of the image to create variations in the dataset. * **SAT5_dataset_10_best_cities_augmented_v2**: These images are improved to remove near black images method using a recursive [forward-backward artefact removal algorithm with inter-band data augmentation on satellite imagery](https://github.com/sebasmos/satellite.extractor/tree/main/src/PART_2_satellite-augmentation). Augmented data with aligned metadata. Improved version using Albumentation wrapper modules with extra augmented data. Data extracted using recursive artifact removal, cloud removal based on LeastCC, and Nearest Interpolation for spatial resolution. Implemented [Notebook](https://github.com/sebasmos/satellite.extractor/blob/main/notebooks/PART_2_satellite_imagery_augmentation.ipynb) and augmentations applied to RGB channels while leaving other satellite channels unchanged. *Pre-processing*: The image augmentation techniques used in this process include various forms of Gaussian noise, implemented through IAAAdditiveGaussianNoise with a probability of 20% and mean zero, and standard deviation of 0.01 * 255 or 0.05 * 255. The GaussNoise technique was also employed with a mean of zero and default variance of (10.0, 50.0). General blurring was implemented through MotionBlur (p=.2), MedianBlur (blur_limit=3, p=0.1), Blur(blur_limit=3, p=0.1), and ShiftScaleRotate(shift_limit=0.0625, scale_limit=0.2, rotate_limit=45, p=0.2). Distortion techniques included OpticalDistortion(p=0.3), GridDistortion(p=.1), IAAPiecewiseAffine(p=0.3), and IAAAffine(scale=(0.8, 1.2), translate_percent=0.1, rotate=15, shear=10, p=0.2). Finally, brightness adjustments were made using CLAHE(clip_limit=2), IAASharpen(), IAAEmboss(), RandomBrightnessContrast(), and HueSaturationValue(p=0.3). ## Sponsors *Project supported by ESA Network of Resources Initiative. Oracle for Research Cloud Credits: “Towards a Smart Eco-epidemiological Model of Dengue in Colombia using Satellite Images” project by the Oracle for Research Program. ## Licensing Information The dataset is released under the terms of MIT. By using this, you are also bound to the respective Terms of Use and License of the original source. ## Author & Mantainer [Sebastián Cajas Ordóñez](https://sebasmos.github.io/) ## Contributors MIT Critical data Colombia: David Restrepo, Kuan-Ting Kuo, Dana Moukheiber, Atika Rahman Paddo, Saptarshi Purkayastha, Leo Anthony Celi, Po-Chih Kuo, Juan Sebastián Osorio-Valencia, Kuan-Ting Ku, Braiam Escobar, Diego M. López, Cheng Che Tsai, Wilson Arbey Diaz, Luis Jesús Martínez, Alessa Álvarez, Siyi Tang, Amara Tariq, Imon Banerjee, Aakanksha Rana, Maria Patricia Arbelaez-Montoy, Cheng Che Tsai, Laura Sofía Daza Rosero, Jhon Fredy Romero Núñez, Wilson Arbey Diaz, Luis Jesús Martínez, Saketh Sundar, Alessa Álvarez, Siyi Tang, Amara Tariq, Imon Banerjee, Aakanksha Rana, Ivan Darío Velez, Maria Patricia Arbelaez-Montoya. ## Citation Please cite our work if you find the resources in this repository useful: Sebastian Andres Cajas Ordoñez, David Restrepo, Kuan-Ting Kuo, Dana Moukheiber, Atika Rahman Paddo, Leo Anthony Celi, Po-Chih Kuo (2022). Towards a Smart Eco-epidemiological Model of Dengue in Colombia using Satellite [Source code]. GitHub. https://github.com/sebasmos/satellite.extractor