Artificial Intelligence Based Crop Disease and Crop Yield Predication in Modern Agriculture

Abstract: Agriculture plays a significant role in the economic sector. The automation in
agriculture is the main concern and the emerging subject across the world. In India, we all know
that Agriculture is the backbone of the country. This system predicts the yield of almost all
kinds of crops that are planted in India. This script makes novel by the usage of simple
parameters like State, district, season, area and the user can predict the yield of the crop. The
paper uses advanced regression techniques and classification algorithms to predict the yield
and uses the concept of Regression for enhancing the algorithms to give a better prediction.
Crop diseases are strongly affected by weather and environmental factors. Weather
fluctuations represent the main factors that lead to potential economic losses. The integration
of forecasting models based on weather data can provide a frame-work for agricultural decision-
making able to suggest key information for overcoming these problems Crop diseases are strongly
affected by weather and environmental factors. Weather fluctuations represent the main
factors that lead to potential economic losses. The integration of forecasting models based on
weather data can provide a frame work for agricultural decision-making able to suggest key
information for overcoming these problems. In the present work, we propose a new artificial
intelligence approach to forecast crop disease in the Maharashtra region and a novel technique
to express a crop disease risk. The experiments conducted are based on historical weather data
as temperature, humidity, rainfall, speed wind collected from several locations over a year. The
tests were aimed to determine the usefulness of the classifier to identify crop– weather–
disease relations for crops and the relative possible outbreak. The results obtained show that
temperature and humidity play a key role in the prediction.

Keywords:- Artificial intelligence, Automation, Yield Prediction, Smart Farming, Machine

Learning, Recommender System, Disease Detection, Classification, etc.
Introduction:
In recent years, an explosion in applications of Artificial Intelligence (AI) specifically in the
domain of health care, weather forecasting, space programs, automation agriculture, etc. has
been observed. Across the globe, more than half of the population is involved in agricultural
practices. In the arena of agriculture, AI is adopted for the planning of farming activities, sales
of agricultural products, weather forecasting, crop disease and yield prediction. Farmers are
taking advantages of AI and getting higher production than traditional farming techniques. In
traditional farming, cultivation was manual process irrigational needs of a crop and its yield was
highly dependent on climate factors throughout the globe. The onset of inventions in industrial
revolution and improvement in mechanisms involved in agricultural practices gave relief to
miserable life of farmers. But still, it is a labor-intensive practice and dependent on mercy of
monsoon.
In agriculture planning to obtain maximum crop yield with restricted area of land is the largest
task in an agro-based country like India. Yield rate of the crop can be increased with the help of
indicators by investigating crop related problems. Crop selection will be more accurate and
beneficial with minimum loss, whether unfavorable condition occurs [10]. Maximum crop yield
can be obtained in favorable growing condition. Improving production rate of crop can be an
important topic for research for the agro-meteorologists, for the development of economic
growth of the country. The two main factors responsible for the yield rate of the crop is, first
one is quality of seeds which can be improved by genetic development using hybridization
technology and second one is the selection of crop based on the favorable and
unfavorable conditions. The two techniques: statistical and machine learning both these
techniques modeled. Many researchers had been tried to get an efficient and accurate model
for crop yielding prediction, soil classification, crop classification, weather predictions [13], crop
disease pre-diction classification of crops [5, 6].
Crop disease prediction is the art of predicting crop yields and production before the harvest
actually takes place, typically a couple of months in advance. Crop forecasting relies on
computer programs that describe the plant environment interactions in quantitative terms.
Data Mining is a process of extracting hidden information from a database and transforms it
into an understandable structure for further use. It is the computational process of discovering
patterns in large data sets involving methods at the intersection of artificial intelligence,
machine learning, statistics, and database systems. The ultimate goal of data mining is
prediction - and predictive data mining is the most common type of data mining and one that
has the most direct business applications. Throughout the years, many algorithms were created
to extract knowledge from large sets of data. There are several different methodologies to
approach this problem: classification, association rule, clustering, etc. Here we will focus on
classification methodology. Classification techniques are designed for classifying unknown
samples using information provided by a set of classified samples.

Literature Survey:
 Vishnu S, A. Ranjith Ram [1]. In this review paper we discuss the various methodologies
for plant disease detection. Studies show that relying on pure naked-eye observation of
experts to detect and classify diseases can be time consuming and expensive, especially in
rural areas and developing countries. So we present fast, automatic, cheap and accurate
image processing based solution. Solution is composed of four main phases; in the first
phase we create a color transformation structure for the RGB leaf image and then, we
apply color space transformation for the color transformation structure. Next, in the
second phase, the images are segmented using the K-means clustering technique. In the
third phase, we calculate the texture features for the segmented infected objects. Finally,
in the fourth phase the extracted features are passed through a pre-trained neural
network.
 Pawan P. Warne, Dr. S. R. Ganorkar [2] This paper presents an approach for careful
detection of diseases, diagnosis and timely handling to prevent the crops from heavy
losses. The diseases on the cotton are critical issue which makes the sharp decrease in the
production of cotton. So for the study of interest is the leaf rather than whole cotton plant
because about 85.95% of diseases occurred on the cotton leaves like Alternaria,
Cercospora and Red Leaf Spot. In this proposal initially preprocessing the input image
using histogram equalization is applied to increase the contrast in low contrast image, K-
 means clustering algorithm is used for segmentation which classifies objects based on a
set of features into K number of classes and finally classification is performed using Neural
network. Thus image processing technique is used for detecting diseases on cotton leaves
early and accurately. It is used to analyze the cotton diseases which will be useful to
farmers.
 Dimitri A. Lisin, Marwan A. Mattar, Matthe w B.Blaschko [3] Object recognition is a central
problem in computer vision research. Most object recognition Systems have taken one of
two approaches, using either global or local features exclusively. This may be in part due
to the difficulty of combining a single global feature vector with a set of local features in a
suitable manner. In this paper, we show that combining local and global features is
beneficial in an application where rough segmentations of objects are available. We
present a method for classification with local features using non-parametric Density
estimation. Subsequently, we present two methods for combining Local and Global
features. The first uses a “stacking” ensemble technique, and the Second uses a
hierarchical classification system. Results show the superior performance of these
combined methods over the component classifiers, with a reduction of over 20% in the
error rate on a challenging marine science application.
 P. R. Rothe, and R. V. Kshirsagar [4] Feature extraction is a significant constituent of a
pattern recognition system. It carries out two assignments: converting input parameter
vector into a feature vector and or reducing its dimensionality. A distinct feature
extraction algorithm makes the classification process more effectual and efficient. The
allocation and recognition of cotton leaf diseases are of the major importance as they
have a cogent and momentous impact on quality and production of cotton. In this work
we present a snake based approach for the segmentation of images of diseased cotton
leaves. We extract Hu’s moments which can be used as shape descriptors for
classification. A theory of two-dimensional moment invariants for planar geometric
figures is also presented. Three diseases have been considered, namely Bacterial Blight,
 P. Revathi, M. Hemalatha, [5] This Proposed Work exposes, a advance computing
technology that has been developed to help the farmer to take superior decision about
 many aspects of crop development process. Suitable evaluation and diagnosis of crop
disease in the field is very critical for the increased production. Foliar is the major
important fungal disease of cotton and occurs in all growing Indian regions. In this work
we express new technological strategies using mobile captured symptoms of cotton leaf
spot images and categorize the diseases using HPCCDD Proposed Algorithm. The classifier
is being trained to achieve intelligent farming, including early Identification of diseases in
the groves, selective fungicide application, etc. This proposed work is based on Image RGB
feature ranging techniques used to identify the diseases (using Ranging values) in which,
the captured images are processed for enhancement first. Then color image segmentation
is carried out to get target regions (disease spots). Next Homogenize techniques like Sobel
and Canny filter are used to identify the edges; these extracted edge features are used in
classification to identify the disease spots. Finally, pest recommendation is given to the
farmers to ensure their crop and reduce the yield loss.

Existing system:
In the existing system is recommendation and disease & crop yield prediction system as per the
weather condition the location given on the bases of the registration area is too much
complicated task. That’s why uncertainties of weather, production, policies, prices, etc. often
lead to mass suicides by farmers. Other thing is that farmers knows the how to proceed some
other crops that’s they can’t be earn maximum profit, they only process the regular crops. So to
address these problems we proposed an Artificial Intelligence Based Recommendation System.

Proposed System:
Data mining is a process of extracting important and useful information from large data sets. It
can be used in field of prediction crop yield. Agriculture in India plays a strategic role in the
economy of the country. The major drawback for the farmers to get the profit is the condition
of global warming that has significant impacts on conditions affecting agriculture. As a result,
the rate of suicide among Indian farmers is increasing drastically which causing impact on the
agricultural economy. In India, majority of the farmers are not getting the expected crop yield
due to several reasons like weather conditions, diseases, soil, water and air which leads to
insecurity of food. Every farmer is interested in knowing, how much yield he is about expect.
Raw data, which is obtained from the history of crop yields, is required for the prediction. These
data play an important role in prediction of crop yield. Data Mining is widely applied to
agricultural problems. Data Mining is used to analyze large data sets and establish useful
classifications and patters in the data sets. The overall goal of the Data Mining process is to
extract the information from a data set and transform it into understandable structure for
further use.
One of the most important aspects when dealing with weather data is how the data from
sensors are processed and analyzed. Most artificial intelligence classifiers require all features to
be complete and a balanced dataset, because the learning phase of classifiers may be biased by
the instances that are frequently present in the dataset or present missing values. To deal with
missing values, the literature has suggested several approaches. The more effective envisages
in removing the noise or in interpolating the data. Different interpolation methods exist. For the
sake of simplicity and due to its effectiveness in our data, we employed the linear interpolation.
To deal with an imbalanced dataset, the researchers recommend two main One of the most
important aspects when dealing with weather data is how the data from sensors are processed
and analyzed. Most artificial intelligence classifiers require all features to be complete and a
balanced dataset, because the learning phase of classifiers may be biased by the instances that
are frequently present in the dataset or present missing values. To deal with missing values, the
literature has suggested several approaches. The more effective envisages in removing the
noise or in interpolating the data. Different interpolation methods exist. For the sake of
simplicity and due to its effectiveness in our data, we employed the linear interpolation. To deal
with an imbalanced dataset, the researchers recommend two main techniques. The first
technique consists of a data-level solution by performing a data sampling, which aims to adjust
the class in an equal distribution in the training set applying over-sampling or under-sampling
methods.
In this work the experiments are performed two important and well known classification
algorithms K Nearest Neighbor (kNN)and Density based clustering are applied to the dataset.
There accuracy is obtained by evaluating the datasets. Each algorithm has been run over the
training dataset and their performance in terms of accuracy is evaluated along with the
prediction done in the testing dataset. The entire analysis process creates a data flow.

Fig.1: System Architecture

Objectives:

The main objectives are

a) To use machine learning techniques to predict crop yield as well as disease.

b) To provide easy to use User Interface.
c) To increase the accuracy of crop yield & disease prediction.
d) To analyze different climatic parameters (cloud cover, Temperature, Humidity, etc.)

Motivation:

• The agricultural yield is primarily depends on weather conditions.

• Farmers necessarily require a timely advice to predict the future crop productivity and
an analysis is to be made in order to help the farmers to maximize the crop production
in their crops with the help of climate change.

• Crop Disease prediction is an important agricultural problem.

• In the past, disease prediction was performed by considering farmer's previous

experience on a particular crop after post condition. We proposed a system for predict
environmental condition on early prediction technique.