Further reading material

Other interesting courses

Labeled data:

https://github.com/Seyed-Ali-Ahmadi/Awesome_Satellite_Benchmark_Datasets
https://github.com/chrieke/awesome-satellite-imagery-datasets
https://github.com/robmarkcole/satellite-image-deep-learning/blob/master/assets/datasets.md
Public tree pointcloud dataset: https://data.mendeley.com/datasets/4gbzk9sy24/1 , publication: https://www.sciencedirect.com/science/article/pii/S0924271620302094
AI datasets by NASA
FLAIR: a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery and code
OpenForest catalog for machine learning in forest monitoring
GLanCE - Global land cover training dataset from 1984 to 2020, publication and dataset
Schmitt et al / Department of Aerospace Engineering, University of the Bundeswehr Munich, Neubiberg, Germany ,There Are No Data Like More Data: Datasets for deep learning in Earth observation

Spatial data:

Rémi Cresson: Deep Learning for Remote Sensing Images with Open Source Software
Géron: Hands-on machine learning with Scikit-Learn & Tensorflow
Murphy: Machine learning: a probabilistic perspective
Bishop: Pattern recognition and machine learning
Hastie, Tibshirani & Friedman: Elements of statistical learning (free PDF)
Mohri, Rostamizadeh & Talwalkar: Foundations of machine learning (free PDF and HTML)
Goodfellow, Bengio, Courville: Deep learning (free HTML)
Justin Morgan Williams: Spatial ML with R
Gwanggil Jeon: Advanced Machine Learning and Deep Learning Approaches for Remote Sensing

SpaceNet challenges
Patrick Gray, Using Neural Networks for Classification and Land Cover Mapping, CNN classification of 32x32 tiles, Keras.
Elias Ayrey, 3D Convolutional Neural Networks with LiDAR, CNN regression of 3D tensors created from lidar data, Tensorflow.
Christoph Rieke, Deep Learning for Instance Segmentation of Agricultural Fields, MXNet.
The Environmental Data Science book has 4 deep learning models presented: 2 for tree crown detection from RGB images, sea ice forecasting and floating objects from Sentinel-2 images.
Caleb Robinson, Building damage assessment
Kris Sankaran, Glacier mapping From Satellite Imagery UNET
Jens Leitloff, Analyzing Sentinel-2 satellite data in Python with TensorFlow.Keras, CNN
Martin Christen, Semantic Segmentation, from GeoPython 20222 conference, CNN with PyTorch
Point cloud semantic segmentation and individual tree segmentation
Estimating tree species composition from airborne laser scanning data using point-based deep learning models with publication

Katarzyna Kopczewska / University of Warsaw, Spatial machine learning: new opportunities for regional science
Ava Vali / Politecnico di Milano, Deep Learning for Land Use and Land Cover Classification Based on Hyperspectral and Multispectral Earth Observation Data: A Review
Monia Digra / Monia Digra Shri Mata Vaishno Devi University, Land use land cover classification of remote sensing images based on the deep learning approaches: a statistical analysis and review
Jürgen Döllner / University of Potsdam, Geospatial Artificial Intelligence: Potentials of Machine Learning for 3D Point Clouds and Geospatial Digital Twins
Marvin Mc Cutchan / TU Wien, Encoding Geospatial Vector Data for Deep Learning: LULC as a Use Case
Younes Charfaoui, Working with Geospatial Data in Machine Learning , feature extration from geospatial data for ML
Behnam Nikparvar / University of North Carolina at Charlotte, Machine Learning of Spatial Data
Aaron E. Maxwell / West Virginia University, Implementation of machine-learning classification in remote sensing: an applied review
Safonova et al / Leibniz Centre for Agricultural Landscape Research (ZALF), Müncheberg, Germany, Deep Learning techniques for adressing small data problems in remote sensing
Calyan Chen et al ,Using time-series imagery and 3DLSTM model to classify individual tree species

ATMU / NLS/FGI, detecting buildings, roads and water-courses, aim to support updating NLS topographic database.
Andras Balazs / LUKE, lidar, forest
Alireza Hamedianfar et al, University of Helsinki, Review of Deep Learning for forest inventory and planning with remote sensing
Joone Laine / Aalto, Crop identification with Sentinel-2satellite imagery in Finland, SVM, RF, MLP and ConvRNN.
Matthieu Molinier / VTT, cloud detection
Matti Mõttus / VTT, hyperspectral data, forest
Janne Mäyrä / SYKE, detetecting tree species from hyperspectral and lidar data, CNN.
Olli Rantanen / University of Helsinki, Liikennemerkkienautomaattinen tunnista-minen panoraamakuvilta, object instance segmentation, YOLO.
Maria Yli-Heikkilä / LUKE, crop prediction based on time-series.