ZinebMEFTAH/Agricultural-Plan-Optimization

This project focuses on optimizing agricultural production in Algeria using Artificial Intelligence (AI) techniques. # Agricultural Plan Optimization An **Artificial Intelligence** project that optimizes agricultural production planning across Algerian regions (wilayas). Given land, cost, and consumption data, it computes production plans that **maximize yield, minimize cost, and improve self-sufficiency** — modeled and solved with classical AI search and constraint techniques. ## Approach The problem is tackled two complementary ways: - **State-space search** — the plan is built incrementally (assigning land use and production per wilaya), with a defined initial state, transition model, goal test, and path cost. - **Constraint Satisfaction (CSP)** — production targets are framed as variables under land, cost, and self-sufficiency constraints. A GUI lets users run the optimization and inspect the resulting plan. ## Data CSV datasets under `DATA/` describe available land, production efficiency, cost structures, consumption needs, and suitable wilayas per product. ## Tech Stack - Python - Search & CSP algorithms (implemented from scratch) - GUI for interaction ## Run ```bash git clone github.com cd Agricultural-Plan-Optimization python SEARCH/gui.py # run the search-based optimizer with its interface python CSP/CSP.py # run the constraint-satisfaction solver ``` ## Project Structure - `SEARCH/` — state-space search solver and GUI (`agriplan.py`, `node.py`, `plan.py`, `gui.py`) - `CSP/` — constraint-satisfaction formulation and solver - `DATA/` — input datasets (CSV) - `Report.pdf` — full project report ## Team Meftah Zineb (lead) · Benamghar Amina · Djoubani Sarah · Benmansour Aya ## Notes Applies classical AI (search + CSP) to a concrete, data-driven optimization problem with real economic and food-security objectives.