A low-cost portable device for crop and fertilizer recommendation
Musoke, Simon Deo
MetadataShow full item record
The agriculture sector in Uganda continues to be important as it employs about 72% of the population and contributes about 32% of the GDP. This project aims at designing and implementing a portable crop and fertilizer recommender device that achieves its function using the readings taken from a 7 in 1 NPK sensor. This will be solving the problems of laboratory soil testing delays and also reducing on the cost expenses. The project concentrates on five crops and these are beans (legumes), maize, banana, sweet potato and tomatoes which were chosen through considering the most crops on daily demand basis in most parts of the country. The product is a Printed Circuit board (PCB) design with all components ( Arduino Uno board, RS485 module, GSM module, 16x4 LCD screen) embedded with it onto which the sensor is connected. Through research from existing soil testing laboratories, we have been able to obtain the key soil parameters required for most crops. In this project therefore, we have highly considered NPK soil nutrients as the key soil nutrients for crop and fertilizer recommendation. The Arduino Uno is programmed in C++, a low level language which makes the operational speeds faster, RS485 module provides a serial communication protocol between the Board and the sensor, 16x4 LCD screen displays the measured NPK values and the GSM module enables data to be sent to firebase as cloud server database. This project is not exhaustive with all soil parameters but only considers key soil parameters, therefore, more soil parameters are expected to be included for future project development. In conclusion, the project could have a wide scope since agriculture is a wide sector. An accurate amount of fertilizer according to the real-time context is the basis of precision agriculture in terms of sustainability and profitability. Many fertilizer’s recommendation systems are proposed without considering the realtime context in terms of soil fertility level, crop type, and soil type. The major obstacle in developing the real-time context-aware fertilizer recommendation system is related to the complexity associated with the real-time mapping of soil fertility. Furthermore, the existing methods of determining the real-time soil fertility levels for the recommendation of fertilizer are costly, time-consuming, and laborious. Therefore, to tackle this issue, we proposed an IoT assisted soil fertility and associated crop mapping to improve the accuracy of the fertilizer recommendation system.