Geospatial APIs For Data Science Applications In Python

Data Science With Google Earth Engine (GEE) and Foursquare With Python Using Application Programming Interfaces (APIs)

What you will learn

Learn how to work with online Jupyter notebooks through

Gain robust grounding in working with geospatial APIs using Python

Apply data science methods on geospatial data

Deploy the Google Earth Engine (GEE) API within the Python ecosystem

Use GEE’s datasets for visualisation and geospatial analysis

Description

ENROLL IN MY LATEST COURSE ON HOW TO LEARN ALL ABOUT OBTAINING AND WORKING WITH WITH FREE GEOSPATIAL DATA OBTAINED VIA APPLICATION PROGRAMMING INTERFACES (APIs) USING DATA SCIENCE TECHNIQUES.

Are you currently enrolled in any of my GIS and remote sensing related courses?
Or perhaps you have prior experiences in GIS or tools like R and QGIS?
You want to quickly analyse large amounts of geospatial data
Implement machine learning models on remote sensing data
You don’t want to spend 100s and 1000s of dollars on buying commercial software for imagery analysis?
You want to have access to a multi-petabyte catalogue of satellite imagery and geospatial datasets with planetary-scale analysis capabilities

The next step for you is to gain proficiency in obtaining free geospatial datasets from a variety of sources, from Foursquare to Google Earth Engine via their Python-friendly APIs and analyse these using data science techniques

MY COURSE IS A HANDS-ON TRAINING WITH REAL REMOTE SENSING AND GIS DATA ANALYSIS WITH GOOGLE EARTH ENGINE- A planetary-scale platform for Earth science data & analysis; including implementing machine learning models on imagery data, powered by Google’s cloud infrastructure. !

My course provides a foundation to carry out PRACTICAL, real-life remote sensing and GIS analysis tasks in this powerful cloud-supported platform. By taking this course, you are taking an important step forward in your GIS journey to become an expert in geospatial analysis.

Why Should You Take My Course?

I have an MPhil (Geography and Environment) from the University of Oxford, UK. I also completed a PhD at Cambridge University (Tropical Ecology and Conservation).

‘;
}});

I have several years of experience in analyzing real-life spatial geospatial data from different sources and producing publications for international peer-reviewed journals.

In this course, actual geospatial data obtained via Foursquare and GEE APIs will be used to give you hands-on experience of applying data science and machine learning techniques to these data to answer real-life questions such as identifying the best locations for a restaurant or changes in socio-economic dynamics of a territory.

This course will ensure you learn & put geospatial data analysis into practice today and increase your proficiency in using APIs for obtaining these data and deriving valuable insights from them.

This is a fairly comprehensive course, i.e. we will focus on learning the most essential and widely encountered data science techniques applied to geospatial data

In addition to all the above, you’ll have MY CONTINUOUS SUPPORT to make sure you get the most value out of your investment!

ENROLL NOW 🙂

Welcome to the Course

What Is This Course About?

Data and Code

Python Installation

What Is Google CoLab?

Google Colabs and GPU

Google Colab Packages

Introduction To Basic Spatial Data Concepts

Introduction to Geospatial APIs (and Other Sources of GIS Data)

What Are APIs

Singapore MRT

Basic Geocoding

Geocode A Dataframe of Cities

Introduction To The Foursquare API

Get Started With the Foursquare API

Obtain Venues and Their Details Around a Particular Location

Visualise the Foursquare Venues

Retrieve Venues On the Basis of Lat Long Coordinates

Retrieve the Venues Corresponding To Mumbai’s Neighbourhoods

Other Source of Geospatial Data

Access Open Street Data

Obtain World Bank Data

Introduction To Google Earth Engine (GE)

What is GEE?

Datasets Within GEE

Obtaining GEE Data Via API To Use With Python

Accessing GEE API Within Python

Introduction To Geemap

Start Exploring Feature Collections

Filter and Visualise Shapefiles

Identify the Biggest Country

Filter Based on Numerical Attributes

Grouping Feature Collections By Attributes

Create a GeoJSON Bounding Box

Clip Image To Shapefile Extent

Upload External Data On GEE

Working With GEE’s Imagery Data

Access Image Collections Within Google Colab

See Images Side By Side

Topographic Computations

Clip Image Collection To Shapefile Extent

Improve Your Clipped Image

Time Series Visualization

What Are Multispectral Data?

Using Multispectral Data: Case of Tonle Sap

Flood Mapping

Why Do We Need Radar Data

Obtaining Sentinel-1 Data From GEE

Visualise Sentinel-1 Data

Obtain Time Series Landsat Data From GEE

Getting a Sense of Our Data

What Are Pandas?

Principles of Data Visualisation

Some Theoretical Principles Behind Data Visualisation

Visualise Time Series Geospatial Data With Pandas

Where Are Singapore’s MRT Stations Located?

Let’s Colour Code These Stations-Part 1

Let’s Colour Code These Stations- Part 2

Machine Learning

What is Machine Learning (ML)?

Training Data

Unsupervised Learning:Theory

k-means

Clustering Landcovers in Cambodia-Part1

Clustering Landcovers in Cambodia-Part 2

Supervised Classification

Random Forest

Basic Supervised Classification With MODIS For Training Samples

How Good Are My Results?

Accuracy

Spectral Unmixing

Supervised Classification With Geolocations: Introduction (Part 1)

Supervised Classification: Geolocation Training Data

Classify The Image

Combine EO Data From Different Sensors-Problem

Supervised Classification: Sentinel-1 and Sentinel-2

Supervised Classification: Sentinel VIs

Visualise the Classification results

Enroll for Free