MEWA: Forecasting Animal Outbreaks for Early Prevention

The Ministry of Environment, Water and Agriculture (MEWA) is a ministry in Saudi Arabia responsible for achieving sustainability of the environment and natural resources in the Kingdom. In its efforts to become a proactive organization that anticipates threats of animal disease epidemics, a predictive use case to forecast animal diseases was built to predict and be prepared in case of emergencies.

Protecting Saudi Arabia’s Food Security

In the Kingdom of Saudi Arabia, millions of livestock are carefully monitored by the ministry as they serve as an essential food source for millions of residents. Ensuring the well-being of such a vital resource is important as animal disease outbreaks can disrupt the economy, food security, and public health. Additionally, certain diseases can even spread from animals to humans, posing serious health risks if not contained.

Forecasting animal diseases is crucial for preventative measures. By using Geographic Information Systems (GIS), a technology that analyzes data based on location, MEWA can predict the likelihood of outbreaks. This allows them to take preventive actions like vaccination programs, biosecurity measures, and movement restrictions to help reduce the spread of diseases among animals.

However, a key challenge for MEWA teams lies in fully utilizing the power of GIS technology. Currently, understanding disease patterns and their seasonal variations across diverse regions with different livestock types requires individual analyses for each disease. This complex task presented serious difficulties that were formidable to overcome.

Optimizing Disease Prediction on the Dataiku Platform

To address the challenges of individual disease analysis, a use case was built with Dataiku’s end-to-end platform.

The use case centers around conducting a time series analysis of animal diseases, factoring in various dimensions such as region, animal type, and specific diseases, along with their various combinations. Furthermore, it incorporates a dynamic selection process, enabling users to choose the dimensions for their predictions.

The flow for the use case is divided into five sub-flows that deviate based on the dimensions included (animals, regions, diseases, offices) to offer more versatility in the prediction outputs for the business users.

The use case flow was divided into six parallel flows as follows:

• Flow 1: Disease forecast and analysis per region per animal
• Flow 2: Disease forecast and analysis per region
• Flow 3: Disease forecast and analysis per animal
• Flow 4: Disease forecast and analysis on the entire Kingdom
• Flow 5: Dynamic in which the user selects the animal, the city, and the disease or multiple diseases

The model undergoes a weekly training regimen to effectively capture new patterns and trends, recalibrate predictions, and identify anomalous behaviour as well as significant shifts in trends. This regular update allows for the most current data to be incorporated, ensuring the precision and relevance of the generated forecasts.

Predictions are visualized on Dataiku using static insights capability allowing the disease experts to navigate through the different diseases and quickly observe the trend analysis, pattern changes, and forecasted number of diseases for the coming 6 months.

Flows 1-4 are run simultaneously by triggering a time-based trigger at the beginning of every week. Each flow then generates results displayed on a dashboard to enable data-driven decision-making. Meanwhile, flow 5 is run through a visual application on command.

This live use case operates on an automation node, pulling data directly from the ministry systems and feeding the analysis results back into the same database. A user-friendly visual application was also created to enable self-service analytics.

With the help of Dataiku, our team was able to organize a workflow that enhanced collaboration between team members and enabled us to work in parallel on different parts of the project simultaneously. Amr Mansour Lead AI Consultant, MEWA

Strengthening Disease Prevention Through Enhanced Forecasting

The main objective of this use case is to empower decision-makers within MEWA to adopt data-driven strategies and proactively combat the spread of animal diseases in the Kingdom. This objective aligns with Saudi Vision 2030 initiative of “Animal Disease Investigation and Control Program” under the strategic objective 5.4.1 “Ensure Development and Food Security.”

With the ministry supervising tens of millions of animals, even small indicators of disease spread can significantly impact both health and monetary values. The use case forecasts and displays the projected number of animals affected by specific diseases in different regions of the kingdom for up to six months in advance. This functionality allows users to monitor trends, detect changes in rates, and anticipate potential outbreaks. Ultimately, it assists the ministry in assessing the effectiveness of disease prevention efforts and health awareness campaigns.

In addition, the visual application grants a more tailored experience by allowing the business user to forecast the spread of a certain disease in a specific MEWA office instead of the whole region, which allows the business users to pinpoint the disease’s hotspot.

Dataiku played its role perfectly by greasing the wheels and always keeping everything needed available and ready. Amr Mansour Lead AI Consultant, MEWA

Maximizing Project Impact Across Every Phase

Throughout the project phases, Dataiku played a crucial role, facilitating seamless progress and efficiency across various tasks:

• Data processing: By leveraging user-friendly visual recipes like the prepare recipe, Dataiku significantly reduced processing time, enabling the team to allocate more attention to other critical project phases.
• Flexibility: Dataiku’s support for Python scripting enabled the use of advanced techniques such as Prophet Facebook for generating time series models, thus enhancing forecasting capabilities.
• Partitioning: The ease of partitioning the extensive dataset (approximately 700,000 observations and 300 partitions) within the platform facilitated the creation of multiple parallel time series, streamlining analysis and improving efficiency.
• Automation: Our automation node simplified workflows, from scenario creation to running flows on a weekly basis, resulting in time savings and ensuring consistency and reliability in analyses.
• Self-service analytics: Dataiku’s visual application capabilities enabled the creation of a tailored self-service analytics app, eliminating the need for extensive programming skills typically required for such solutions.

During the project phases, Dataiku proved to be invaluable in every step along the way. Amr Mansour Lead AI Consultant, MEWA