A Machine Learning-based Approach for Crop Yield Prediction and Fertilizer Recommendation

IEEE BASE PAPER ABSTRACT:

Agriculture plays a critical role to Indian global economy and contributes a major part to GDP. With the expansion of the human population, it is necessary to maintain food security, it is achieved and controlled by the agricultural yield produced by the nation. The yield of a crop is mainly determined by the climatic conditions like temperature, rainfall, soil conditions, and fertilizers. Due to these variable factors, the production gets affected and remains a huge problem for the agricultural sector to strengthen the need for exactness for proper analyzing the crop production in variable climatic conditions. Recently, the machine learning algorithms are used by the researchers to predict the yield of a crop before its actual cultivation. This research study has proposed a machine learning algorithm: AdaBoost to predict the yield of crops based on the parameters like state, district, area, seasons, rainfall, temperature, and area. To enhance the yield, this research study also suggests a fertilizer based on the soil conditions like NPK values, soil type, soil PH, humidity, and moisture. Fertilizer recommendation is primarily done by using the Random Forest [RF] algorithm.

PROJECT OUTPUT VIDEO:

ALGORITHM / MODEL USED:

Extra Trees Regressor, Gaussian NB.

OUR PROPOSED ABSTRACT:

The foundation of a developing nation like India is agriculture. The majority of the people rely on agriculture for income. Agriculture practices are being modernized today for the benefit of the farmers. An emerging area of informatics called machine learning can be used to great effect in the agriculture sector. For agricultural stakeholders, fertilizer recommendations and crop output forecasting are crucial.

The weather, environmental changes, rainfall (which can be unpredictable at times), water management, and fertilizer use all have a significant impact on crop yield or production. These changeable factors have a negative impact on productivity, which makes it even more important to be precise when properly analyzing crop yield under changing climatic conditions. As a result, growers are unable to produce the crop’s predicted yield.

Today, a variety of researchers apply data mining, machine learning, and deep learning techniques to boost and improve crop productivity and quality. The proposed approach builds a collaborative system for predicting crop yield and recommending fertilizer. In this project, a system is created that uses agricultural datasets, where the Extra Trees Regressor algorithm is used to recommend the right production yield, and additionally, our suggested system employs fertilizer datasets, where the GaussianNB algorithm is used to suggest the right fertilizer.

Utilizing our proposed system for crop yield prediction and fertilizer recommendations would undoubtedly boost agricultural output. This approach supports decisions on fertilization that are beneficial to farmers. The accuracy of this system is around 99% for Crop yield prediction and 100% for fertilizer recommendation.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

System : Pentium i3 Processor.
Hard Disk : 500 GB.
Monitor : 15’’ LED
Input Devices : Keyboard, Mouse
Ram : 4 GB

SOFTWARE REQUIREMENTS:

Operating System : Windows 10 / 11.
Coding Language : Python 3.8.
Web Framework : Flask.
Frontend : HTML, CSS, JavaScript.

REFERENCE:

Jeevaganesh R; Harish D; Priya B, “A Machine Learning-based Approach for Crop Yield Prediction and Fertilizer Recommendation”, IEEE Conference, 2022.

Python IEEE Projects

A Machine Learning-based Approach for Crop Yield Prediction and Fertilizer Recommendation