Completed Project(s)
Building Open Source NLP Libraries & Tools for the Arabic Language
The problem
1. Arabic is the 5th most spoken language in the world and the 1st language of the Arab world countries, making it extremely important worldwide.
2. Arabic is grammatically complex and has free order properties, which all pose significant challenges in Arabic NLP applications.
3. There are 3 types that characterize Arabic, including Classical Arabic, Modern Standard Arabic & Dialect Arabic.
4. Tools built by big tech and accessible to the majority of the world are limited to translating only a few of the most popular languages.
The Project Outcomes
The envisioned deliverables can be broken down into two main areas:
1. Build open-source Arabic NLP libraries for sentiment analysis, morphological modeling, dialect identification, and named entity recognition
2. Build 5:8 core functions to support Arabic NLP (lemmatization, stop words, tokenizing text, word embedding, part of speech tagging.. etc.) like NLTK but for Modern Standard Arabic.
Source Code: https://github.com/OmdenaAI/Arabic-Chapter
Demo: https://www.youtube.com/watch?v=PaWCX2IG7eo
Preventing Gang and Gun Violence via Social Media Analysis
The Project Goals
This 4-week project aims to help uncover how we can predict violence and gang actions from analyzing social tweets and communities. We will achieve this by :
1. Scrapping relevant data from different social media platforms; mainly tweets and Facebook.
2. Cleaning, processing, and labeling the data.
3. Implementing well-known algorithms and libraries such as Girvan Newmann algorithm, NetworkX, to analyze and detect communities.
4. Training different machine learning models to classify violence from non-violent tweets.
5. Evaluating and visualizing the results.
You will also have the chance to write about your experience on the Omdena blog, putting your work in front of more than 19,000 of Omdena’s social media.
Source Code: https://github.com/OmdenaAI/omdena-iraq-gun-violence
Desertification Detection with Deep Learning and Satellite Data (completed)
The Background
According to Savory.global “Desertification is the persistent degradation of dryland ecosystems by variations in climate and human activities.”
In other words, it is making what used to be arable farming land into useless one. It is one of the greatest environmental challenges today and unfortunately mostly targets the world’s poorest population.
Desertification leads to so many other problems from affecting the agricultural sector leading to more hunger, to increasing the displacement of people who used to live on these lands yields and what used to be green fields, which in return have its own set of problems.
Fortunately, though, most of this degradation can be reversed and treated by many methods that’s why many reports have been published addressing this important topic and demanding immediate actions. It is also why most of the countries suffer from it, due to obvious disregard by the authorities of these regions and countries.
The Problem
1. According to recent reports, the rate of desertification in Iraq has increased to 39% and 54% of the country’s agricultural land faces drought and land degradation.
2. According to a report by the Republic of Iraq Ministry of Agriculture, Iraq is losing 100 square kilometers annually from its arable lands as a consequence of desertification.
3. Iraq’s highly excessive dependence on water that comes outside of its borders, the mismanagement of water, inefficient farming habits and the already dry climate makes it more vulnerable to climate change.
4. Having more reliable sources to know where to focus the efforts could be the beginning of solving this huge challenge and providing immediate help to the most endangered regions.
The Project Goals
AI has proven to provide more and more accurate forecast results in recent years, allowing the formulation of solutions in a faster and agile way than before.
Here we’ll work to harvest this technological advancement to help predict the most areas and regions that could fall victim to desertification in the upcoming years in Iraq.
That is why for 4 weeks our goal will be to produce a forecasting model to predict the status of different land covers in Iraq. This will include working on the following:
1. Collect free and publicly available Satellite data that covers Iraq over the years and in different seasons.
2. Using Supervised and Unsupervised learning algorithms to classify different land type covers.
3. Analyze the loss of green, degradation of lands in Iraq over the years (using NDVI, NDWI, and other indices), and build a forecast model based on that information.
4. Build a dashboard visualizing the areas affected and the future prediction using streamlit or other freely available tools.
The Learning Outcomes
1. Geospatial and Satellite data that will include learning the basics and advanced techniques to process satellite data.
2. Implement supervised and unsupervised machine learning and deep learning algorithms to classify different land types.
3. Building a dashboard to visualize and present our results in an impactful way.
4. The project will include conducting multiple workshops on the above topics
The Tasks & Timeline
|
Week 1 |
Week 2 |
Week 3 |
Week 4 |
|
–Task1: Data collection – Task 3/4: The models research phase |
–Task1:Data collection –Task2:Data pre-processing –Task 3/4: The models research phase –Task 3/4: Testing & Choosing the best Models |
–Task2:Data pre-processing –Task 3/4: Implementing the models –Task 5: preparation for data visualization |
–Task 3/4: Implementing the models –Task 5: Data visualization and Deployment |
Iraq Chapter Lead(s)
