Update README.md

README.md

@@ -554,7 +554,7 @@ Several different techniques can be used to count the number of objects in an im
 * [Electric-Pylon-Detection-in-RSI](https://github.com/qsjxyz/Electric-Pylon-Detection-in-RSI) -> a dataset which contains 1500 remote sensing images of electric pylons used to train ten deep learning models
 * [Synthesizing Robustness YOLTv4 Results Part 2: Dataset Size Requirements and Geographic Insights](https://www.iqt.org/synthesizing-robustness-yoltv4-results-part-2-dataset-size-requirements-and-geographic-insights/) -> quantify how much harder rare objects are to localize
 * [IS-Count](https://github.com/sustainlab-group/IS-Count) -> IS-Count is a sampling-based and learnable method for estimating the total object count in a region. 
-* [Object Detection On Aerial Imagery Using RetinaNet](https://towardsdatascience.com/object-detection-on-aerial-imagery-using-retinanet-626130ba2203) -> ESRI Data Science Challenge 2019 3rd place solution
+* [Object Detection On Aerial Imagery Using RetinaNet](https://towardsdatascience.com/object-detection-on-aerial-imagery-using-retinanet-626130ba2203)
 * [Clustered-Object-Detection-in-Aerial-Image](https://github.com/fyangneil/Clustered-Object-Detection-in-Aerial-Image)
 * [yolov5s_for_satellite_imagery](https://github.com/KevinMuyaoGuo/yolov5s_for_satellite_imagery) -> yolov5s applied to the DOTA dataset
 * [RetinaNet-PyTorch](https://github.com/HsLOL/RetinaNet-PyTorch) -> RetinaNet implementation on remote sensing ship dataset (SSDD)
@@ -963,6 +963,7 @@ More general than change detection, time series observations can be used for app
 * [dl-time-series](https://github.com/NexGenMap/dl-time-series) -> Deep Learning algorithms applied to characterization of Remote Sensing time-series
 * [tpe](https://github.com/jnyborg/tpe) -> code for 2022 [paper](https://openaccess.thecvf.com/content/CVPR2022W/EarthVision/html/Nyborg_Generalized_Classification_of_Satellite_Image_Time_Series_With_Thermal_Positional_CVPRW_2022_paper.html): Generalized Classification of Satellite Image Time Series With Thermal Positional Encoding
 * [wildfire_forecasting](https://github.com/Orion-AI-Lab/wildfire_forecasting) -> code for 2021 [paper](https://arxiv.org/abs/2111.02736): Deep Learning Methods for Daily Wildfire Danger Forecasting. Uses ConvLSTM
+* [satellite_image_forecasting](https://github.com/rudolfwilliam/satellite_image_forecasting) -> predict future satellite images from past ones using features such as precipitation and elevation maps. Entry for the [EarthNet2021](https://www.earthnet.tech/) challenge
 
 ## Crop yield
 * [Crop yield Prediction with Deep Learning](https://github.com/JiaxuanYou/crop_yield_prediction) -> code for the paper Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data
@@ -1143,7 +1144,6 @@ Translate images e.g. from SAR to RGB.
 * [Seamless-Satellite-image-Synthesis](https://github.com/Misaliet/Seamless-Satellite-image-Synthesis) -> generate abitrarily large RGB images from a map
 * [How to Develop a Pix2Pix GAN for Image-to-Image Translation](https://machinelearningmastery.com/how-to-develop-a-pix2pix-gan-for-image-to-image-translation/) -> article on machinelearningmastery.com
 * [Satellite-Imagery-to-Map-Translation-using-Pix2Pix-GAN-framework](https://github.com/anh-nn01/Satellite-Imagery-to-Map-Translation-using-Pix2Pix-GAN-framework)
-* [SAR to RGB Translation using CycleGAN](https://www.esri.com/arcgis-blog/products/api-python/imagery/sar-to-rgb-translation-using-cyclegan/) -> uses a CycleGAN model in the ArcGIS API for Python
 * [RSIT_SRM_ISD](https://github.com/summitgao/RSIT_SRM_ISD) -> PyTorch implementation of Remote sensing image translation via style-based recalibration module and improved style discriminator
 * [pix2pix_google_maps](https://github.com/manishemirani/pix2pix_google_maps) -> Converts satellite images to map images using pix2pix models
 * [sar2color-igarss2018-chainer](https://github.com/enomotokenji/sar2color-igarss2018-chainer) -> code for 2018 paper: Image Translation Between Sar and Optical Imagery with Generative Adversarial Nets
@@ -1511,6 +1511,7 @@ Measure surface contours & locate 3D points in space from 2D images. NeRF stands
 * [AGSDNet](https://github.com/RTSIR/AGSDNet) -> code for 2022 [paper](https://ieeexplore.ieee.org/abstract/document/9755131): AGSDNet: Attention and Gradient-Based SAR Denoising Network
 * [LFG-Net](https://github.com/Evarray/LFG-Net) -> code for 2022 [paper](https://ieeexplore.ieee.org/abstract/document/9815311): LFG-Net: Low-Level Feature Guided Network for Precise Ship Instance Segmentation in SAR Images
 * [sar_sift](https://github.com/yishiliuhuasheng/sar_sift) -> Image registration algorithm
+* [SAR-Despeckling](https://github.com/ImageRestorationToolbox/SAR-Despeckling) -> toolbox
 
 ## NVDI - vegetation index
 * Calculated via band math `ndvi = np.true_divide((ir - r), (ir + r))` but challenging due to the size of the imagery
@@ -1534,6 +1535,8 @@ Measure surface contours & locate 3D points in space from 2D images. NeRF stands
 * [DeepCalib](https://github.com/alexvbogdan/DeepCalib) -> A Deep Learning Approach for Automatic Intrinsic Calibration of Wide Field-of-View Cameras
 * [PerceptualSimilarity](https://github.com/richzhang/PerceptualSimilarity) -> LPIPS is a perceptual metric which aims to overcome the limitations of traditional metrics such as PSNR & SSIM, to better represent the features the human eye picks up on
 * [Optical-RemoteSensing-Image-Resolution](https://github.com/wenjiaXu/Optical-RemoteSensing-Image-Resolution) -> code for 2018 [paper](https://www.mdpi.com/2072-4292/10/12/1893): Deep Memory Connected Neural Network for Optical Remote Sensing Image Restoration. Two applications: Gaussian image denoising and single image super-resolution
+* [Hyperspectral-Deblurring-and-Destriping](https://github.com/ImageRestorationToolbox/Hyperspectral-Deblurring-and-Destriping)
+* [HyDe](https://github.com/Helmholtz-AI-Energy/HyDe) -> Hyperspectral Denoising algorithm toolbox in Python, with [paper](https://arxiv.org/abs/2204.06979)
 
 ## Neural nets in space
 Processing on board a satellite allows less data to be downlinked. e.g. super-resolution image might take 8 images to generate, then a single image is downlinked. Other applications include cloud detection and collision avoidance.
@@ -2265,7 +2268,7 @@ An overview of the most relevant services provided by AWS, Google and Microsoft.
 * [AWS App Runner](https://aws.amazon.com/blogs/containers/introducing-aws-app-runner/) enables quick deployment of containers as apps
 * [AWS Athena](https://aws.amazon.com/athena/) allows running SQL queries against CSV files stored on S3. Serverless so pay only for the queries you run
 * If you are using pytorch checkout [the S3 plugin for pytorch](https://aws.amazon.com/blogs/machine-learning/announcing-the-amazon-s3-plugin-for-pytorch/) which provides streaming data access
-* [Amazon AppStream 2.0](https://aws.amazon.com/appstream2/) is a service to securely share desktop apps over the internet, see this post on [sharing access to ArcGIS Pro](https://www.esri.com/arcgis-blog/products/arcgis-pro/administration/arcgis-pro-streamed-from-the-cloud-yes/)
+* [Amazon AppStream 2.0](https://aws.amazon.com/appstream2/) is a service to securely share desktop apps over the internet
 * [aws-gdal-robot](https://github.com/mblackgeo/aws-gdal-robot) -> A proof of concept implementation of running GDAL based jobs using AWS S3/Lambda/Batch
 * [Building a robust data pipeline for processing Satellite Imagery at scale](https://medium.com/fasal-engineering/building-a-robust-data-pipeline-for-processing-satellite-imagery-at-scale-808700b008cd) using AWS services & Airflow
 * [Using artificial intelligence to detect product defects with AWS Step Functions](https://aws.amazon.com/blogs/compute/using-artificial-intelligence-to-detect-product-defects-with-aws-step-functions/) -> demonstrates image classification workflow