| dc.contributor.author | Muhammad Azan Ali, 01-135212-052 | |
| dc.contributor.author | Mahmood Mazhar, 01-135212-036 | |
| dc.date.accessioned | 2026-02-18T07:06:02Z | |
| dc.date.available | 2026-02-18T07:06:02Z | |
| dc.date.issued | 2025 | |
| dc.identifier.uri | http://hdl.handle.net/123456789/20602 | |
| dc.description | Supervised by Ms. Mona Leeza | en_US |
| dc.description.abstract | Farmers use the mobile-based Smart Agriculture System to resolve their primary issues regarding crop maintenance and plant wellness concerns. The system implements Flutter to create its platform interface which synchronizes data through Firebase and delivers AI functionalities through Flask APIs. The platform provides two essential services. Users can perform functions from the Smart Agriculture System through its two main features: Crop Recommendation System utilize weather and soil data to create recommendations and the Pest and Disease Detection module analyzes plant images with AI for solutions. The database tools represent essential components for farmers who need to enhance their productivity and take decisions based on data. Modern farmers need the system to address their primary challenges with unpredictable weather conditions along with insufficient rural support and traditional farming practices. The combination of these problems hinders their ability to pick suitable crops and identify plant diseases before they become problematic. Through its application of intelligent technologies the Smart Agriculture System functions as a link to help farmers transform their practice of farming more responsive and efficient and reduce their dependence on unpredictable traditional approaches. In this project mobile technology serves alongside cloud services and AI to make up this entire system. Through its Flutter interface the system allows farmers to operate a simple user-friendly interface on various devices. All data is stored and synchronized instantaneously in the Firebase backend system to provide farmers with current information. The machine learning models run through Flask-based AI APIs. The platform operates two distinct functions with one model that suggests crops selection based on soil and weather information and another model that identifies plant diseases by processing user-submitted images. Users gain access through a single platform which provides farmers realtime information to make decisions to increase their production and minimize their losses. | en_US |
| dc.language.iso | en | en_US |
| dc.publisher | Computer Sciences | en_US |
| dc.relation.ispartofseries | BS(IT);P-3047 | |
| dc.subject | Smart | en_US |
| dc.subject | Agriculture | en_US |
| dc.subject | System | en_US |
| dc.title | Smart Agriculture System | en_US |
| dc.type | Project Reports | en_US |