ECSA 2025
Mon 15 - Fri 19 September 2025 Limassol, Cyprus
Fri 19 Sep 2025 11:30 - 11:45 at Phoenix - Session 7 - LLMs in Software Architecture (II) Chair(s): Salah Sadou

Agriculture is a significant contributor to global water consumption, making the optimization of irrigation practices essential for sustainability. CropX, an agritech startup, seeks to automate irrigation event detection using large-scale Volumetric Water Content (VWC) data from IoT sensors. Ensuring scalability and accuracy is vital for decision-making within CropX’s farm management system.

This paper describes the development of scalable machine learning (ML) models to automate irrigation detection in large, unbalanced datasets. We discuss the architectural patterns and software design decisions that enable these models to be effectively deployed within an AI-driven system, emphasizing MLOps and CI/CD practices. Multiple ML models were tested, including statistical methods (ARIMA, Kalman Filter), ano-maly detection techniques (Isolation Forest), and ensemble approaches. These were evaluated using performance metrics such as F1 score, precision, and recall. Additionally, we highlight the role of human-in-the-loop strategies in refining model predictions, showcasing the interaction between agronomists and AI-driven recommendations.

Our contribution includes an analysis of the software architecture used for deploying ML models, focusing on microservices, data pipelines, and scalable cloud-based solutions. We illustrate how this system integrates with existing farm management platforms and discuss its implications for future AI-based agent systems in precision agriculture.

The ensemble models achieved superior performance, significantly improving the F1 score compared to individual models. Their integration into CropX’s infrastructure enhanced irrigation event detection while optimizing resource usage. A robust software architecture supports continuous integration and model evolution, ensuring system scalability.

Fri 19 Sep

Displayed time zone: Athens change

11:00 - 12:30
Session 7 - LLMs in Software Architecture (II)Research Papers / Industry Program at Phoenix
Chair(s): Salah Sadou IRISA, University of South Brittany
11:00
30m
Full-paper
Automated Software Architecture Design Recovery from Source Code Using LLMsResearch Track Paper
Research Papers
Tiziano Santilli Gran Sasso Science Institute (GSSI), Marco De Luca University of Naples Federico II, Domenico Amalfitano University of Naples Federico II, Anna Rita Fasolino Federico II University of Naples, Patrizio Pelliccione Gran Sasso Science Institute, L'Aquila, Italy
File Attached
11:30
15m
Short-paper
AI-Driven Machine Learning Architecture for Scalable Irrigation Detection in Precision Agriculture: A Case Study with CropXIndustry Track Paper
Industry Program
Jakub Ozimek University of Groningen, Jakub Ozimek University of Groningen, Andrea Capiluppi University of Groningen
11:45
15m
Short-paper
Exploring Architectural Smells Detection Through LLMsResearch Track Paper
Research Papers
Claudio Tessa University of Milano-Bicocca, Matteo Bochicchio University of Milano-Bicocca, Francesca Arcelli Fontana University of Milano-Bicocca
12:00
15m
Short-paper
LLM-based Quality Assessment of Software Architecture Diagrams: A Preliminary Study with Four Open-Source ProjectsResearch Track Paper
Research Papers
Glauber Oliveira University of Fortaleza, Nabor Mendonca University of Fortaleza