Syam Kakarla

Data Science | Remote Sensing

Satellite Imagery Meets Computer Vision: A Tutorial for wildfire detection in Australia using Python

Image for post
Image for post
Photo by Michael Held on Unsplash

Over the past decade, Mother Earth has been harmed by unprecedented wildfires. A wildfire can be described as an uncontrollable fire that is spreading across the Wildland, Forests, Grassland, e.t.c. Wildfires have a huge impact on Humans, Nature, and the Economy and these are the major cause of greenhouse gas emissions.

The Majority of the wildfires are caused by humans practices such as agriculture burning. The below animation shows the wildfire data in 2019 across the world collected by NASA’S Moderate Resolution Imaging Spectroradiometer (MODIS) satellite. …


Detailed Explanation

Use the power of Transfer Learning

Image for post
Image for post
Source: https://github.com/facebookresearch/detectron2

Table of Contents

  • What is Detectron2?
  • Project Setup
  • Build the Model
  • Training and Evaluation
  • Results
  • Resources

What is Detectron2?

Detectron2 is an opensource object recognition and segmentation software system that implements state of the art algorithms as part of Facebook AI Research(FAIR). It is a ground-up rewrite in PyTorch to its previous version Detectron, and it originates from MaskRCNN-Benchmark.

You can see the details of Detectron2 along with the benchmark comparisons, different applications, customizations, and brief up on nuts and bolts of its working nature from PyTorch DevCon19.

YouTube: PyTorch

The Detectron also provides a large collection of baselines trained with Detectron2 and you can access…


PySpark Tutorial

Chapter 1: Introduction to PySpark using US Stock Price Data

Image for post
Image for post
Photo by Luke Chesser on Unsplash

PySpark is an API of Apache Spark which is an open-source, distributed processing system used for big data processing which was originally developed in Scala programming language at UC Berkely. The Spark has development APIs in Scala, Java, Python, and R, and supports code reuse across multiple workloads — batch processing, interactive queries, real-time analytics, machine learning, and graph processing. It utilizes in-memory caching, and optimized query execution for fast analytic queries against data of any size. …


Hands-on Tutorials, Data science | Remote sensing | Hands-on Tutorial

Different methods and Machine Learning techniques to analyze satellite imagery using Python with hands-on tutorials and examples.

Image for post
Image for post
Photo by USGS on Unsplash

This article helps users to understand the different methods and supervised and unsupervised machine learning techniques to analyze satellite imagery using Python with hands-on tutorials and examples.

Contents

  1. Introduction to Satellite Imagery
  2. Landsat8 and Sentinel-2 Satellites
  3. Satellite Imagery Indices
  4. Supervised Learning in Satellite Imagery
  5. Unsupervised Learning in Satellite Imagery
  6. Conclusion

Let’s get started ✨

Introduction to Satellite Imagery

Satellite imagery has a wide range of applications that is incorporated in every aspect of human life. Especially remote sensing has evolved over the years to solve a lot of problems in different areas.

Remote sensing is the process of detecting and monitoring the physical characteristics of…


Remote Sensing | Data Analysis | Python

A detailed explanation of Data Analysis on Sundarbans Satellite Imagery using Python

Image for post
Image for post
Photo by USGS on Unsplash

This article helps readers to better understand the satellite data and different methods to explore and analyze the Sundarbans satellite data using Python.

Table of Contents

  1. Introduction to Remote Sensing
  2. Sundarbans Satellite Imagery
  3. Data Analysis
  4. Vegetation and Soil Indices
  5. Water Indices
  6. Geology Indices
  7. Conclusion
  8. References

Let’s get started ✨

Introduction to Remote Sensing

Remote sensing is the process of detecting and monitoring the physical characteristics of an area by measuring it's reflected and emitted radiation at a distance (typically from satellite or aircraft). Special cameras collect remotely sensed images, which help researchers “sense” things about the Earth.

Electromagnetic energy, produced by the vibration of charged particles, travels…


Python | Machine Learning | Remote Sensing

A simple tutorial on Ground Truth labeling of satellite imagery using K-Means Clustering Algorithm using Python

Image for post
Image for post
Image by Tuna Ölger from Pixabay

In Research w.r.t Supervised Machine Learning problems, we often encounter data that has no labels. Data labeling is the process of identifying raw data (images, text files, videos, etc.) and adding one or more meaningful and informative labels to provide context so that a machine learning model can learn from it.

It is no different when compared to problems in remote sensing, Here we need to define a label for every pixel of the satellite imagery which is further used to train machine learning models for land cover classification, finding objects, e.t.c.

The ground truth labeling can be divided into…


Data Science

A simple guide to PySpark SQL functions with intuitive examples.

Image for post
Image for post
Photo by Lanju Fotografie on Unsplash

This article covers an explanation of PySpark SQL functions using the United States Stock Price data.

Table of Contents

  1. Introduction
  2. Setting Environment in Google Colab
  3. Creating a Spark Session
  4. Reading U.S Stock Price Data
  5. Aggregation Functions
  6. Window Functions
  7. Conclusion

Introduction

PySpark is an API of Apache Spark which is an open-source, distributed processing system used for big data processing which was originally developed in Scala programming language at UC Berkely. The Spark has development APIs in Scala, Java, Python, and R, and supports code reuse across multiple workloads — batch processing, interactive queries, real-time analytics, machine learning, and graph processing. It utilizes in-memory caching…


Data Science | Data Visualization

Embed your interactive plots in Medium, Webpages, and other platforms using Plotly and Chartstudio

Image for post
Image for post
Photo by William Iven on Unsplash

There is no such thing as information overload. There is only a bad design. — Edward Tufte

We all know a picture is worth a thousand words, data visualization is the visual summary of the information that makes it easier to understand/identify patterns and trends instead of looking at thousands of rows in spreadsheets. A good data visualization place the meaning of complex datasets in a precise and concise way. An interactive data visualization makes it even easier to understand and find insights from the data.

This article covers creating different interactive plots using Plotly and embedding interactive data visualizations…


Machine Learning | Remote Sensing

An unsupervised learning approach for Sundarbans satellite Imagery Analysis using Python

Image for post
Image for post
Photo by ImaginEarth La Terre En Images on Unsplash

This article helps readers to better understand the Sundarbans satellite data and to perform dimensionality reduction and clustering with Python.

Table of Contents

  1. Introduction to Remote Sensing
  2. Sundarbans Satellite Imagery
  3. Dimensionality Reduction
  4. k-Means Clustering
  5. Conclusion
  6. References

Let’s Get Started✨

Introduction to Remote Sensing

Remote sensing is the process of detecting and monitoring the physical characteristics of an area by measuring it's reflected and emitted radiation at a distance (typically from satellite or aircraft). Special cameras collect remotely sensed images, which help researchers “sense” things about the Earth.

Electromagnetic energy, produced by the vibration of charged particles, travels in the form of waves through the atmosphere and the…


Deep Learning | Remote Sensing

A Python hands-on tutorial on Land Cover Classification of Satellite Imagery using Convolutional Neural Networks.

Image for post
Image for post
Photo by USGS on Unsplash

Land cover classification using remote sensing data is the task of classifying pixels or objects whose spectral characteristics are similar and allocating them to the designated classification classes, such as forests, grasslands, wetlands, barren lands, cultivated lands, and built-up areas. Various techniques have been applied to land cover classification, including traditional statistical algorithms and recent machine learning approaches, such as random forest and support vector machines, e.t.c.

This article covers a hands-on Python tutorial on the land cover classification of satellite imagery using Convolutional Neural Network (CNN).

Table of Contents

  1. Introduction
  2. Convolutional Neural Networks (CNN)
  3. Salinas HSI
  4. Implementation of CNN
  5. Training
  6. Results
  7. Conclusion

Syam Kakarla

Machine Learning Practitioner and Data Science Enthusiast, https://www.linkedin.com/in/syam-kakarla/

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store