How to Apply Machine Learning Techniques in GIS and Remote Sensing.
When you have large data sets of satellite or drone imagery that you have to process to create predictions, classification, or clustering – machine learning (ML) is the way to go. Indeed, ML has started to play a critical role in spatial problem solving given its potential to rapidly scan and unlock insights from petabytes of pixels obtained from hundreds of satellites and drones that are constantly orbiting earth.
Orbital Insight, for example, applies machine learning and computer vision technologies to interpret data at petabyte scale to make it actionable for better business and policy decisions. The California based company has developed a powerful method that blends satellite imagery, deep learning, and data science for monitoring fresh-water supplies at local and global scale.
Open-Source Machine Learning Tools and Libraries
Based on python, scikit-learn is an opensource set of tools for data mining and analysis. Built on NumPy, SciPy, and matplotlib, it allows you to easily and efficiently automate image recognition or classification using custom algorithms such as SVM, nearest neighbors and random forest.
MLIB is Apache Spark’s scalable machine learning library. It boosts many common algorithms and usable data types, designed to run at speed and scale. Although its based on Java, MLlib fits into Spark‘s APIs and interoperates with NumPy in Python (as of Spark 0.9) and R libraries (as of Spark 1.5). So if you prefer either R or Python you can still work with MLIB.
Skynet machine Learning platform is a product of Development Seed.
Skynet includes a suite of tools for analyzing massive amounts of satellite imagery using machine learning and open data. At the core of Skynet is SegNet, a machine learning framework for analyzing photo pixels. Skynet is designed to support open algorithm development.
Google TensorFlow is an open source software library for numerical computation. It was originally developed for the purposes of conducting machine learning and deep neural networks research. But the system is general enough to be applicable in a wide variety of other domains as well. Tensorflow has been successfully used in a number of remote sensing projects including on the automatic detection of land-use patterns in Chinese cities.
Keras and Estimator APIs allows you to work with Tensorfow using R interface. TensorFlow API also allows you to work with Python.
If you know of any other open-source or even commercial Machine Learning platform, kindly share with us so we we can enrich and enlighten others.