AquaGPT: A Multimodal Transformer Framework with Expert Knowledge Embedding for Intelligent Feeding Management in Aquaponics

Dianyou Kang ^1,2, Yi Yang ^1,2, Oliver Lexter July A. Jose ¹, Ralph Gerard B. Sangalang ¹, Antonette V. Chua ¹ and Anton Louise P. De Ocampo ^1,*

1 Department of Electronics Engineering, Batangas State University, Batangas City 4200, Philippines
2 Information Technology Department, Jiangmen Technician College, Jiangmen 529090, China
* Correspondence: antonlouise.deocampo@ieee.org

(Received: 5 February 2026 Revised: 27 March 2026 Accepted: 13 April 2026 Published: 17 April 2026)

ABSTRACT

Aquaponics integrates aquaculture with hydroponic crop cultivation, which offers a sustainable approach to food production. However, feeding management remains a critical bottleneck because it directly affects feed efficiency, water quality stability, and ecosystem balance. This paper proposes AquaGPT, a multimodal Transformer framework that embeds expert knowledge to address challenges in feeding management in aquaponic systems. The system employs a distributed sensing network, processed by modality-specific encoders and projected into a shared embedding space, to capture synchronized acoustic, sensor, environmental, and visual data. A differentiable expert rule layer embedding seven aquaculture feeding management rules then aligns predictions with established aquaculture practice to improve interpretability. A dynamic weight allocation strategy further enhances robustness by prioritizing reliable modalities under noisy or incomplete input conditions. Experiments on the Full Fish Interaction Analysis (FFIA) dataset demonstrate that AquaGPT outperforms state-of-the-art multimodal fusion baselines by up to 4.5% accuracy under severe noise. Also, it achieves a 30% reduction in parameters compared to similar models, enabling real-time deployment on edge devices. These results highlight AquaGPT’s potential for precision aquaponics and demonstrates capability to optimize feeding strategies, which theoretically improves resource efficiency and mitigates the environmental footprint.

Key words: aquaponics; intelligent feeding management; multimodal fusion; spatiotemporal transformer; expert knowledge embedding; precision aquaculture