Farmer's Analytical assistant
•
0 likes•47 views
This document discusses a proposed system called the Farmer's Analytical Assistant, which aims to help farmers in India maximize crop yields through predictive analysis and recommendations. It analyzes agricultural data on factors like soil properties, rainfall, and past crop performance using machine learning techniques to predict optimal crops for different regions based on the environmental conditions. The proposed system would allow farmers to input local data, receive personalized yield predictions and crop suggestions, and get advice from experts online. The methodology section describes how climate/rainfall and soil data is collected and analyzed using machine learning models to provide crop recommendations. The goal is to improve upon traditional crop selection methods and help increase farmers' incomes.
Report
Share
![Farmer’s Analytical Assistant
Aishwarya Jadhav, Ankita Mande, Dhanashree Gurav, Meghana Sarje
Under the guidance of S.S.Kare
Information Technology Department , VPKBIET, Baramati
Abstract— Agriculture is the one of the source of liveli-
hood for approximately 58 percent of Indias population
primarily depends on agriculture, and it is the most
crucial part of GDP to Indian economy which is not
satisfactory.There are many reasons behind India’s poor
production in agriculture field like lack of crop planning
by farmers or various environmental and economical fac-
tors that influence the crop production but unpredictable
changes in these factors lead to a great loss to farmers.
To reap high-quality appropriate crop desire for areas
primarily based on parameters like soil conditions, rainfall
and weather we have got applied gadget studying 3
method. By using data mining, machine learning crop yield
can be predicted by deriving useful patterns from these
agricultural data that helps farmers to decide the crop
they would like to plant for the upcoming year for gaining
maximum profit.With the assist of disorder assessment
tool, we predict the crop and marketplace assessment at
the equal time as cultivation of any crop.
Index Terms—Crop yield prediction, Agriculture, Data Min-
ing,Machine learning.
I. INTRODUCTION
Data mining is the process which is used to find out
useful patterns from large amount of data. It can be used
for identifying clusters in data, and includes set of rules that
describes each category or class in a data set.It is also used
to find out hidden, valid, and useful patterns in huge data
sets. Data Mining is all about discovering previously unknown
relationships amongst the data.Data mining is also called
as Knowledge discovery, Knowledge extraction, data/pattern
analysis, information harvesting, etc..[9] Data Mining is the
method of extraction, transforming, loading and predicting
the meaningful information from huge data to extract some
patterns and also transform it into understandable structure
for further use[9].
One of the reason for the poor contribution of the agricultural
sector to the Indian economy may be the lack of adequate
crop planning by farmers as well as by the government. Rapid
fluctuations in crop prices are common in the market. In such
a scenario, it is difficult for a farmer to make an educated
choice of crop to grow in their land or to estimate the yield
and price to expect from it.
By applying farmers previous experience for a particular crop,
one can make the predictions for crop but For the better crop
production, the farmers definitely requires a suitable guidance
to predict the future of crop yield and also an analysis is to be
made in order to help the farmers to increase crop production
for their crops. As every farmer is interested in knowing that
how much yield is expected to be grown in their land .
In this paper we analysed different techniques to maximize
and predict the crop yield productions.
II. LITERATURE SURVEY
The research by X.E. Pantazi et al. [1] by understanding
yield restricting variables requires high goals multi-layer
data about elements influencing crop development and yield.
Consequently, on-line proximal soil detecting for estimation
of soil properties is required, because of the capacity of
these sensors to gather high goals information (1500 test
per ha), and in this manner decreasing work and time cost
of soil examining and examination. The point of this paper
is to foresee inside field variety in wheat yield, in light of
on-line multi-layer soil information, and satellite symbolism
edit development attributes. Managed self-sorting out maps
equipped for dealing with existent data from various soil and
product sensors by using an unsupervised learning calculation
were utilized.
The research by Michael D. Johnson et al. [3] is about
Harvest yield estimate models for grain, canola and spring
wheat developed on the Canadian Prairies were created
utilizing vegetation records got from satellite information
and machine learning techniques. Hierarchical bunching
was utilized to assemble the harvest yield information
from 40 Census Agricultural Regions (CARs) into a few
bigger locales for building the figure models. The Normalized
Difference Vegetation Index (NDVI) and Enhanced Vegetation
Index (EVI) got from the Moderate-goals Imaging Spector-
radiometer (MODIS), and NDVI were considered as indicators
for harvest yields. Different direct relapse (MLR) and two
nonlinear machine learning models Bayesian neural systems
(BNN) and model-based recursive apportioning (MOB)
were utilized to gauge trim yields, with different blends of
MODIS-NDVI, MODISEVI and NOAA-NDVI as indicators.
Anshal Savla, Parul Dhawan, Himtanaya Bhadada, Nivedita
Israni, Alisha Mandholia, Sanya Bhardwaj [4] they made
Survey of classification algorithms for formulating yield
prediction accuracy in precision agriculture This Paper
makes a relative study of categorization algorithms and their
performance which helps to know the yield and predict it in
precision agriculture.](https://cdn.statically.io/img/image.slidesharecdn.com/ijsred-v3i5p16-200919142838/85/Farmer-s-Analytical-assistant-1-320.jpg)
More Related Content
What's hot
What's hot (20)
Similar to Farmer's Analytical assistant
Similar to Farmer's Analytical assistant (20)
More from IJSRED
More from IJSRED (20)
Recently uploaded
Recently uploaded (20)
Farmer's Analytical assistant
- 1. Farmer’s Analytical Assistant Aishwarya Jadhav, Ankita Mande, Dhanashree Gurav, Meghana Sarje Under the guidance of S.S.Kare Information Technology Department , VPKBIET, Baramati Abstract— Agriculture is the one of the source of liveli- hood for approximately 58 percent of Indias population primarily depends on agriculture, and it is the most crucial part of GDP to Indian economy which is not satisfactory.There are many reasons behind India’s poor production in agriculture field like lack of crop planning by farmers or various environmental and economical fac- tors that influence the crop production but unpredictable changes in these factors lead to a great loss to farmers. To reap high-quality appropriate crop desire for areas primarily based on parameters like soil conditions, rainfall and weather we have got applied gadget studying 3 method. By using data mining, machine learning crop yield can be predicted by deriving useful patterns from these agricultural data that helps farmers to decide the crop they would like to plant for the upcoming year for gaining maximum profit.With the assist of disorder assessment tool, we predict the crop and marketplace assessment at the equal time as cultivation of any crop. Index Terms—Crop yield prediction, Agriculture, Data Min- ing,Machine learning. I. INTRODUCTION Data mining is the process which is used to find out useful patterns from large amount of data. It can be used for identifying clusters in data, and includes set of rules that describes each category or class in a data set.It is also used to find out hidden, valid, and useful patterns in huge data sets. Data Mining is all about discovering previously unknown relationships amongst the data.Data mining is also called as Knowledge discovery, Knowledge extraction, data/pattern analysis, information harvesting, etc..[9] Data Mining is the method of extraction, transforming, loading and predicting the meaningful information from huge data to extract some patterns and also transform it into understandable structure for further use[9]. One of the reason for the poor contribution of the agricultural sector to the Indian economy may be the lack of adequate crop planning by farmers as well as by the government. Rapid fluctuations in crop prices are common in the market. In such a scenario, it is difficult for a farmer to make an educated choice of crop to grow in their land or to estimate the yield and price to expect from it. By applying farmers previous experience for a particular crop, one can make the predictions for crop but For the better crop production, the farmers definitely requires a suitable guidance to predict the future of crop yield and also an analysis is to be made in order to help the farmers to increase crop production for their crops. As every farmer is interested in knowing that how much yield is expected to be grown in their land . In this paper we analysed different techniques to maximize and predict the crop yield productions. II. LITERATURE SURVEY The research by X.E. Pantazi et al. [1] by understanding yield restricting variables requires high goals multi-layer data about elements influencing crop development and yield. Consequently, on-line proximal soil detecting for estimation of soil properties is required, because of the capacity of these sensors to gather high goals information (1500 test per ha), and in this manner decreasing work and time cost of soil examining and examination. The point of this paper is to foresee inside field variety in wheat yield, in light of on-line multi-layer soil information, and satellite symbolism edit development attributes. Managed self-sorting out maps equipped for dealing with existent data from various soil and product sensors by using an unsupervised learning calculation were utilized. The research by Michael D. Johnson et al. [3] is about Harvest yield estimate models for grain, canola and spring wheat developed on the Canadian Prairies were created utilizing vegetation records got from satellite information and machine learning techniques. Hierarchical bunching was utilized to assemble the harvest yield information from 40 Census Agricultural Regions (CARs) into a few bigger locales for building the figure models. The Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI) got from the Moderate-goals Imaging Spector- radiometer (MODIS), and NDVI were considered as indicators for harvest yields. Different direct relapse (MLR) and two nonlinear machine learning models Bayesian neural systems (BNN) and model-based recursive apportioning (MOB) were utilized to gauge trim yields, with different blends of MODIS-NDVI, MODISEVI and NOAA-NDVI as indicators. Anshal Savla, Parul Dhawan, Himtanaya Bhadada, Nivedita Israni, Alisha Mandholia, Sanya Bhardwaj [4] they made Survey of classification algorithms for formulating yield prediction accuracy in precision agriculture This Paper makes a relative study of categorization algorithms and their performance which helps to know the yield and predict it in precision agriculture.
- 2. Aakunuri Manjula, Dr.G.Narsimha XCYPF [5]: A Flexible and Extensible Framework for Agricultural Crop Yield Prediction This concludes the requirement for crop yield prediction and its major usage and the role in a nations planned guiding principle which are made in agriculture development field. III. OBJECTIVES AND GOALS Agriculture is the main base of Indian economy. The agriculture is the most important economical sector in our county. The farmers totally depends on the crop production and their farms for economical gain. The yield is based on cli- mate conditions such as rainfall structure. It highly influences agriculture. So there is need of farmers and agriculturalists, they require spontaneous guidance proposition in predicting future reaping instances to maximize crop yield. IV. EXISTING SYSTEM APPROACH Agriculture is the principle base of Indian financial sys- tem. In India, farmer used crop selection method is only conventional technique. The agriculture technology is the most vital and powerful financial quarter in our county. The farmers are absolutely relying on the vegetation and their farms for least expensive gain. The yield obtained generally relies upon on climate situations as rainfall patterns largely influence cultivation methodologies. So, want of farmers and agriculturalists require a spontaneous recommendation. proposition in predicting upcoming reaping times to maximise crop . In traditional manner on machine gaining knowledge of and agriculture analysis we came throughout the truth that traditionally crop choice techniques is not pleasing the farmers cost effective delight. We are confronted such a lot of issues in present paintings. Due to incorrect or flawed crop choice approach GDP is likewise low V. PROPOSED SYSTEM APPROACH Agriculture is necessary in the of economy in India. In current years because of industrialization excessive use of insecticides the electricity of soil is getting affected. Many of the methods observed through agriculture aren’t enough to growth the productivity. The commonplace problem gift the various Indian farmers are they dont have any data regarding the correct crop primarily based on their soil requirements so it impacts the productivity. Thus, we try to prove the current crop selection technique influences on farmers within your means ability by using degrading yield boom. So, we invent the effective crop choice technique primarily based on machine learning (SVM). We advise the first-class appropriate crop for the regions thinking about environmental conditions. Agriculture is the backbone for a growing economy like India and there is a sizable need to preserve the rural sustainability. We are going to offer one solution for all make our system smart and virtual vicinity for agriculture. This system contains following modules- Fig. 1. Block Diagram • Farmer -Register, login, enter environmental details, view yields prediction and crop suggestions, ask runtime queries. • Admin -Register, login, view farmers details, view all crop details, update crop details and monitor system. • Expert Advisor -Register, login, upload blogs videos, success stories, help farmers, solve queries, and provide dynamic assistance. VI. METHODOLOGY A. DATASET GATHERING There are two data sets used for the our model. The first contains historic district-wise rainfall data for Pune districts of Maharashtra. The gathering period spans to 10 years from 2010 to 2018. Rainfall is measured in millimetres and the labelled volume for a District is the mean of values recorded at all the weather stations in the District. The other data set contains a detailed description about the soil properties recorded in Pune District of Maharashtra recorded over 10 years. Soil properties include the concentration of Nitrogen, Phosphorous and Potassium (NPK) in the soil (all in tones), the scales of pH of the soil, amongst others. Every row of values is labelled with a corresponding Yield value expressed in tones per hectare. The trained model proposed in this paper curates results of the model trained on rainfall data with the machine learning model trained on other soil properties 1) Climate and Rainfall: At the Western Ghat and hill area is cool and eastern area having hot and dry climate. The maximum temperature of pune district ranges between 34 and 410C in April-May, while the minimum temperature varies
- 3. between 50C to 100C in the months of November to January. The average annual rainfall at the district is 675mm, most of which is receive through South-West monsoon. However, medium rainfall region at district having on average rainfall of 900 mm, eastern region have an average between 600 to 700 mm while western region have an average of 1171 mm5. The regularity in occurrence in recent years has not experienced in the district. 2) Soil and Topography : Pune region possesses mainly three types of soils, viz. black-fertile, brown and mixed type. In western region soil, type has brown and low quality where as eastern region having fertile and plain type. The richest alluvial soil track found in the Valley of Bheema River. The rivers Velu, Ghod are left side of Bheema and Indrayani, Bhama, Mula-Mutha etc. are at right side. Each tahsil of the district have minimum one river6. Therefore, the agro-climatic condition of region is favourable. VII. ALGORITHM USED SVM finds its place in this work for training the Recom- mendation system with training set. It is also used after the classification using yields data based on environmental factors. Algorithm works as follows: Because of this undesirable information existing in the input data, both during training and classification, the pre-processor fails to identify the exact accuracy, thus failing to perform with improved efficiency.The parameter for the crops like climatic factor, moisture and past dataset can be used to predict the yield of the crop. Collection of more valid details of soil class, latitude, longitude and suitable crop can greatly accelerate the efficiency of work. The pre-training unit could hence be improved and a lot more features can be extended, thus significantly contributing towards the agricultural welfare worldwide[7 8]. Input of training set containing appropriate crops for given soil class and rainfall data. Output will in the form of crop recommendation for current region. VIII. RESULTS In our experimental setup, Below describes our system modules and respective generated output. Sr no. No.of Input parameters Output Generated 1. Soil samples of all regions in pune NPK summarization of all regions 2. Average rain- fall dataset Generated vector av- erage rainfall 3. Temperature parameter Average temperature class 4. All Envi- ronmental parameters Best suitable Crop suggestion list 5. All area of farm Crop Yield predic- tion 6. Crop and yield details Current market eval- uation Fig. 2. Input parameters Fig. 3. Output generated. We proposed assistive system for economical welfare of farmers.We are creating support vector machine algorithm for classifying environmental factors.The environmental factors arelike soil types with NPK values, 10 years rainfall dataset, and temperature dataset.The trained model is constructed
- 4. based on temperature,soil types and rainfall data. The trained model gives us bestsuitable crop selection which solves existing crop selection problem.The average yield dataset for all crops is used from Google source for prediction of yields. IX. CONCLUSION The farmers can match the best advisable weather conditions for the cultivation of any crop. The crops which are commercial crop can be considered in the predictions of system so the loss can be avoided. Unlike this more crop productions can be predicted. The methodologies can be used with data of other crops to study their relationship with essential climatic parameters. From the above analysis, SVM and Non-Linear Regression shows an average accuracy of less than 10 percent difference between the predicted and actual market price[13]. Non-Linear Regression algorithm increases the accuracy of system and SVM is used to analyze the past data of various attributes. REFERENCES [1] Aakash G Ratkal, Gangadhar Akalwadi, Vinay N Patil and Kavi Mahesh, Farmers Analytical Assistance, IEEE International Conference on Cloud Computing in Emerg- ing Markets 2016. [2] ”A study of Rainfall over India Using Data Mining” Chowdari K.K,Dept.of Computer Science and Engineering BGS Institute of Technology Bellur Cross,Karnataka,India. [3] Mansa Manjunatha,Parkavi A,Estimation of Arecanut Yield in Various Climatic Zones of Karnataka using Data Mining Technique : A Survey. [4] Aakunuri Manjula, Dr.G.Narsimha (2015), ”XCYPF: A Flexible and Extensible Framework for Agricultural Crop Yield Prediction” , Conference on Intelligent Systems and Control (ISCO). [5] A.ShanningBao, S. Cao, C.Ni, X.Xu, M.Ju, H.He, Q.Zhou(2017). Crop yield variation trend and distribu- tion pattern in recent ten years. 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). [6] B.Kulkarni, S.Mandal, S.N.Sharma, G.S.Mundada, M.R.Meeradevi.(2018). Predictive Analysis to Improve Crop Yield using a Neural Network Model. International Conference on Advances in Computing, Communications and Informatics (ICACCI). [7] Udayan Birajdar, Sanket Gadhave, Shreyas Chikodikar, Shubham Dadhich, Shwetambari Chiwhane, Detec- tion and Classification of Diabetic Retinopathy Using AlexNetArchitecture of Convolutional Neural Networks, Proceeding of International Conference on Computational Science and Application, online 05 January 2020, pp 245- 253. [8] Dr. C. Nalini, Shwetambari Kharabe, Sangeetha S, Effi- cient Notes Generation through Information Extraction, International Journal of Engineering and Advanced Tech- nology (IJEAT) ISSN: 2249 8958, Volume-8 Issue-6S2, August 2019 [9] F.Kogan, N.Kussul, T.Adamenko, S.Skakun, O.Kravchenko, O.Kryvobok, A.Shelestov, A.Kolotii, O.Kussul, and A.Lavrenyuk, Winter wheat yield forecasting in ukraine based on earth observation, meteorological data and biophysical models, International Journal of Applied Earth Observation and Geoinformation, vol.23,pp.192203, 2013. [10] H.Boogaard, C.Van Diepen, R.Rotter,J.Cabrera and H.Van Laar, Wofost 7.1 ; users guide for the wofost 7.1 crop growth simulation model and wofost control center 1.5, SC-DLO, Tech. Rep., 1998. [11] https://www.guru99.com/data-mining-tutorial.html