Muhammad Umar

Developed diverse maps using Python programming and Google Earth Engine (GEE).
Constructed an artificial intelligence system for classifying maps, focusing on deforestation, forestation, and biomass.
Used FastAPI to manage and process multiple maps efficiently.
Leveraged Python, Google Cloud Platform (GCP), Google Cloud Service, Geo-Pandas, Pandas, Scikit-learn, NumPy, SQL, FastAPI, S3, GCS, and Bash.

✨ Key responsibilities:
Google Earth Engine Development:
Write source code in Python to create multiple maps. Create AI system for classification such as deforestation, forestation or biomass maps.
Backend development:
Backend development (Fast-API) to handle multiple map
Classification:
Optical Classification via SAR Sentinal
✨ Technologies Used:
Python, GCP, Google Cloud Service, Geo-Pandas, Pandas, Scikit-learn, NumPy, SQL, Fast-API, S3, GCS, Bash, Gunicorn,
👉 Skills:
Artificial Intelligence (AI) · Predictive Analytics · Data Modeling · Object-Oriented Programming (OOP) · preprocessing · Data Management · Modeling · Postgre SQL · Statistical Modeling · Python (Programming Language) · Machine Learning · Data Analysis

• Automated Data Scrapping Pipeline: Developed and maintained an automated data scrapping pipeline, extracting valuable information from databases. Implemented a seamless process to save the acquired data back into databases.
• Data Annotation Pipeline: Established an automated pipeline dedicated to preprocessing, analyzing, and annotating the scraped data. Successfully stored the enriched data in MongoDB, ensuring efficiency and accuracy.
• ML/DL CI/CD Pipeline: Constructed a robust Continuous Integration/Continuous Deployment (CI/CD) pipeline for machine learning and deep learning models. Integrated the modeling pipeline with data scrapping and annotation processes, optimizing the overall workflow.
• Django REST API Development and AWS Deployment: Developed Django REST API for seamless interaction with AI/ML models. Achieved successful deployment of AI/ML models on Amazon Web Services (AWS), showcasing expertise in cutting-edge technologies.
• Technologies Expertly Utilized: Proficiently utilized a comprehensive array of technologies including Python, Scrapy, Selenium, BeautifulSoup4, Pandas, Scikit-learn, NumPy, MongoDB, Lime, Django, DRF, Flask, FastAPI, Airflow, Redis, Docker, Kubernetes, AWS, MySQL, S3, EC2, Bash, SonarQube, Semgrep, Horusec, Bendit, and Insider, NLTK, SpaCy, and Hugging Face Transformers.

• Automated Data Scrapping Pipeline: Developed and maintained an automated data scrapping pipeline, extracting valuable information from databases. Implemented a seamless process to save the acquired data back into databases.
• Data Annotation Pipeline: Established an automated pipeline dedicated to preprocessing, analyzing, and annotating the scraped data. Successfully stored the enriched data in MongoDB, ensuring efficiency and accuracy.
• ML/DL CI/CD Pipeline: Constructed a robust Continuous Integration/Continuous Deployment (CI/CD) pipeline for machine learning and deep learning models. Integrated the modeling pipeline with data scrapping and annotation processes, optimizing the overall workflow.
• Django REST API Development and AWS Deployment: Developed Django REST API for seamless interaction with AI/ML models. Achieved successful deployment of AI/ML models on Amazon Web Services (AWS), showcasing expertise in cutting-edge technologies.
• Technologies Expertly Utilized: Proficiently utilized a comprehensive array of technologies including Python, Scrapy, Selenium, BeautifulSoup4, Pandas, Scikit-learn, NumPy, MongoDB, Lime, Django, DRF, Flask, FastAPI, Airflow, Redis, Docker, Kubernetes, AWS, MySQL, S3, EC2, Bash, SonarQube, Semgrep, Horusec, Bendit, and Insider, NLTK, SpaCy, and Hugging Face Transformers.

Developed and maintained an automated data scraping pipeline.
Extracted valuable information from databases.
Implemented a process to save acquired data back into databases.
Established an automated pipeline for preprocessing, analyzing, and annotating scraped data.
Stored enriched data in MongoDB.
Constructed a Continuous Integration/Continuous Deployment (CI/CD) pipeline for machine learning and deep learning models.
Integrated the modeling pipeline with data scraping and annotation processes.
Developed Django REST API for interaction with AI/ML models.
Deployed AI/ML models on Amazon Web Services (AWS).
Utilized Python, Scrapy, Selenium, BeautifulSoup4, Pandas, Scikit-learn, NumPy, MongoDB, Lime, Django, DRF, Flask, FastAPI, Airflow, Redis, Docker, Kubernetes, AWS, MySQL, S3, EC2, Bash, SonarQube, Semgrep, Horusec, Bendit, Insider, NLTK, SpaCy, and Hugging Face Transformers.

• Data Functions: Spearheaded data acquisition initiatives, sourcing satellite data via FTP, GPS data from field surveys, UAV drone data, and Spectro-radiometer inputs. Conducted thorough data analysis and preprocessing, laying the foundation for subsequent tasks.
• Executed supervised classification using Machine Learning (ML), excelling in cartography and mapping endeavors.
• Utilized Technologies: Demonstrated expertise in employing a diverse set of technologies, including Python, NumPy, Pandas, QGIS, Arcpy, bash, GPS, and Machine Learning.
• Masterful Problem Solver and AI Enthusiast: Expertise in machine learning algorithms, artificial intelligence, predictive analytics, data modeling, natural language processing (NLP), statistical modeling, Python programming, and Geographic Information Systems (GIS).

Spearheaded data acquisition initiatives.
Sourced satellite data via FTP, GPS data from field surveys, UAV drone data, and spectro-radiometer inputs.
Conducted data analysis and preprocessing.
Executed supervised classification using Machine Learning (ML).
Worked in cartography and mapping endeavors.
Used Python, NumPy, Pandas, QGIS, Arcpy, bash, GPS, and Machine Learning.

Selected as a mentor at the International NASA Space App competition in 2019.
o Deliver a lecture on ‘How data can transform solutions on Earth and beyond?’
o Provide mentorship to the groups of students preparing projects for NASA Hackathons
o Judge the projects to select the best of them.

Selected as a mentor at the International NASA Space App competition in 2019.
o Deliver a lecture on ‘How data can transform solutions on Earth and beyond?’
o Provide mentorship to the groups of students preparing projects for NASA Hackathons
o Judge the projects to select the best of them.

Worked on Carbon Credit Identification for Pakistan using the Landsat dataset.
Integrated satellite data with Google Maps.
Performed validation using millions of samples collected through digitization.
Utilized a random forest algorithm.
Applied supervised classification techniques of Machine Learning to extract forest area data.
Used Python, Google Earth Pro, LULC classification, Data Cleaning, Data Sampling, Digitization, Modeling, and Machine Learning.

• Carbon Credit Identification for Pakistan: Utilization of Landsat Dataset: In the pursuit of achieving Carbon Credit Identification for the entire country of Pakistan, the project harnessed the power of the Landsat dataset.
• Integration and Validation: The integration of satellite data with Google Maps was seamlessly executed, followed by a meticulous validation process. Millions of samples were collected through digitization to ensure accuracy.
• Application of Supervised Classification Techniques: . The project utilized a random forest algorithm, and samples were meticulously acquired through manual referencing. To extract forest area data, state-of-the-art Supervised Classification techniques of Machine Learning were employed
• Technologies and Tools Utilized: The project leveraged a comprehensive set of technologies, including Python, Google Earth Pro, LULC classification, Data Cleaning, Data Sampling, Digitization, Modeling, and Machine Learning.
• Skills Demonstrated: The successful execution of this project showcased a diverse skill set, including proficiency in Problem Solving, Machine Learning Algorithms, Algorithms, Artificial Intelligence (AI), Predictive Analytics, Data Modeling, Statistical Modeling, Python (Programming Language), Geographic Information Systems (GIS), and Machine Learning.

• Field Survey for Environmental Monitoring: Undertook extensive field surveys to monitor and assess environmental conditions.
• IEE Report Writing and Maintenance: Authored comprehensive reports following the Environmental Impact Assessment (EIA) guidelines and actively maintained them for accuracy and relevance.
• Advocacy for EPA at Public Hearings: Played a pivotal role in representing the Environmental Protection Agency (EPA) at public hearings, effectively communicating environmental concerns and proposed solutions.
• Data Entry and Digitization Proficiency: Demonstrated adeptness in data entry and digitization processes, ensuring the accurate recording and preservation of essential information.

Undertook extensive field surveys to monitor and assess environmental conditions.
Authored comprehensive reports following Environmental Impact Assessment (EIA) guidelines.
Maintained reports for accuracy and relevance.
Represented the Environmental Protection Agency (EPA) at public hearings.
Demonstrated data entry and digitization processes.