Aryo Wiryawan
Founder and Chairman
JALA Tech
Indonesia
Email: aryo@jala.tech
Aryo Wiryawan is the Founder and Chairman of JALA Tech, a startup working to help the shrimp industry achieve better sustainability using big data and IoT technology. JALA developed a water quality monitoring device and farm management system to ensure data driven decision-making systems in the farms and throughout the supply chain. Aryo has been farming shrimp since 2001 when he first helped his father manage family farms in Pekalongan, Indonesia, while also building a Software Development company with his college friends in Yogyakarta. This gave Aryo the opportunity to develop a unique view in both shrimp and digital technology that drove him to start JALA in 2015.
| Session 3 | Managing Productivity with EHP Mitigation |
| Presentation | AI and Big Data Analytics to Predict Trigger Points for AHPND, IMNV and WSD in Shrimp Ponds in Indonesia |
Abstract
The intensive nature of Asian shrimp farming has resulted in exceeding the natural carrying capacity, which has consequently led to a higher prevalence of diseases.
AI and big data analytics can play a crucial role in disease prevention and management. By analyzing large volumes of data, AI algorithms can detect patterns and early warning signs of diseases, allowing farmers to take proactive measures. Real-time monitoring systems powered by AI can track water quality parameters, detect anomalies, and in the future trigger automated interventions to maintain optimal conditions for shrimp health.
To help farmers in mitigating the impact of disease we have developed a predictive model which can provide early warning of disease occurrences. We focused on predicting acute hepatopancreatic necrosis disease (AHPND), infectious myonecrosis virus (IMNV), and white spot disease (WSD). We used data from 1839 crop cycles. The cycles are managed by 383 farms. The data covered 4 physical parameters measured twice daily (in the morning and evening). Those parameters are water temperature, dissolved oxygen, salinity, and pH. The data also covers disease diagnosis.
Applying the algorithms to these crop data, we managed to achieve F1 scores higher than 0.85 for these three diseases. However, there is a performance issue in prediction of IMNV where we only obtained a 0.78 recall score which indicates a high false negative prediction. Despite this, in this research, we are convinced that the disease occurrence can be predicted based on water quality conditions.
Furthermore, the integration of AI and automation can enhance sustainability by optimizing resource utilisation. AI algorithms can analyse data on feed consumption, environmental factors, and growth patterns to develop precise feeding strategies. This reduces feed waste and minimises environmental impacts. Automation can also contribute to efficient water and energy management, reducing resource consumption and improving overall sustainability.
In conclusion, the integration of AI, big data, and automation presents promising opportunities for mitigating disease risks and increasing sustainability in Asian shrimp farming. By harnessing the power of these technologies, farmers can proactively manage diseases, optimise resource utilization, and improve operational efficiency, leading to a more sustainable and resilient shrimp farming industry.
