Research Article
AI-Driven Agricultural Advisor: Real-Time, Multilingual Support with Lang Graph & Weather APIs
Neha Bansal
,
Bhawna Singla*
Issue:
Volume 13, Issue 2, June 2025
Pages:
22-30
Received:
9 May 2025
Accepted:
21 May 2025
Published:
19 June 2025
Abstract: This research introduces the development of a smart AI agent using LangGraph to provide real-time, location-specific agricultural recommendations to farmers. Leveraging the integration of AgroMonitoring weather APIs, the system collects and analyzes live weather data such as temperature, rainfall, humidity, and soil moisture, which are crucial for agricultural decision-making. By combining this weather data with decision tree-based algorithms, the AI agent predicts optimal crop choices, suggests irrigation practices, and offers rainwater harvesting strategies tailored to the farmer's specific region. The use of decision trees ensures that these recommendations are not only data-driven but also interpretable, allowing farmers to understand the reasoning behind the advice. Furthermore, the AI agent incorporates multilingual support to enhance accessibility. It translates agricultural advice into local languages, such as Hindi, Tamil, and Marathi, making the system inclusive and usable for a diverse range of farmers across different regions of India. This feature significantly reduces language barriers, enabling farmers from various linguistic backgrounds to engage with the technology more effectively. The paper delves into the workflow of the system, from data collection to backend implementation using LangGraph, and discusses its broader impact on promoting sustainable farming practices. By providing farmers with timely, personalized insights, the AI agent empowers them to make informed decisions that improve crop yields, optimize resource use, and contribute to long-term agricultural sustainability. Ultimately, this approach aims to foster a more resilient and productive agricultural landscape, benefiting both farmers and the environment.
Abstract: This research introduces the development of a smart AI agent using LangGraph to provide real-time, location-specific agricultural recommendations to farmers. Leveraging the integration of AgroMonitoring weather APIs, the system collects and analyzes live weather data such as temperature, rainfall, humidity, and soil moisture, which are crucial for ...
Show More
Research Article
Reinforcement Learning Based Neuro-fuzzy Controller for Coffee Roasting Process
Abiy Amare*,
Solomon Seid
Issue:
Volume 13, Issue 2, June 2025
Pages:
31-48
Received:
15 July 2025
Accepted:
28 July 2025
Published:
26 August 2025
DOI:
10.11648/j.acis.20251302.12
Downloads:
Views:
Abstract: Supervised learning is mainly used to optimize Adaptive Neural Fuzzy Inference System (ANFIS) controllers. In order to generate data for supervised learning, a controller is designed and optimized using Particle Swarm Optimization (PSO) or any other algorithms. This paper proposes and compares reinforcement learning based ANFIS and Approximate Reasoning Intelligent controller (ARIC) controllers. Reinforcement learning based ANFIS reduces the work flow required to train it by directly optimizing the membership functions using Proximal Policy Optimization (PPO) algorithm. ANFIS and ARIC neuro fuzzy controllers are designed for nonlinear dynamics of coffee roasting process using Schwartzberg’s model. A custom layer is designed for every membership function and fuzzy inference operations using MATLAB’s Deep Learning Toolbox. This neural connectionist model of ANFIS and ARIC is used as actor. The critic which evaluates the goodness of action taken is a two-layer neural network with sigmoidal activation function. Simulink environment is also created to represent the dynamics of coffee roasting process. The agent is trained to track roast profile for 50 episodes. The training converged at 50th iteration. After training, the Root Mean Square Error (RMSE) for ARIC architecture reduced from 0.5134 to 0.08122. Similarly, the RMSE of ANFIS improved from 0.2026 to 0.0624.
Abstract: Supervised learning is mainly used to optimize Adaptive Neural Fuzzy Inference System (ANFIS) controllers. In order to generate data for supervised learning, a controller is designed and optimized using Particle Swarm Optimization (PSO) or any other algorithms. This paper proposes and compares reinforcement learning based ANFIS and Approximate Reas...
Show More
