BSc (Computer Science) Final Year Project Proposal

Name: Muhammad Hussaini Ahmad

ID- Number: 20/08/05/511
Proposed Topic: Machine Learning for Predicting Crop Yield in Maiduguri
Supervisor: Dr. Emmanuel Gbenga Dada

1.0 Introduction

In developing countries, farming is considered as the major source of revenue for many people.
In modern years, the agricultural growth is engaged by several innovations, environments,
techniques and civilizations. In addition, the utilization of information technology may change
the condition of decision making and thus farmers may yield the best way. For decision making
process, data mining techniques related to the agriculture are used. Data mining is a process of
extracting the most significant and useful information from the huge number of datasets.
Nowadays, we used machine learning approach with developed in crop or plant yield prediction
since agriculture has different data like soil data, crop data, and weather data. Plant growth
prediction is proposed for monitoring the plant yield effectively through the machine learning
techniques. It is also applicable for the automated process of farming is the beginning of a new
era in Maiduguri that will be suitable for the farmers who seek experts to take suggestion about
the appropriate crop on specific location of their land and don’t want to forget any step of the
cultivation throughout the process. Although, the opinion from experts is the most convenient
way, this application is designed to give accurate solution in fastest manner possible. This
research’s main objective is to bring farming process a step closer to the digital platform.

Agriculture is an economic activity that has a high dependency on weather conditions. This
means that seasonal agriculture is dependent on natural weather conditions, also known as
rainfed agriculture. Rainfed agriculture constitutes 80% of the cropland worldwide and generates
good yields when crops have favorable weather conditions. In many lands where rainfall is
scarce, rainfed agriculture is supplemented by irrigation practices. The fact still remains that
agricultural production is heavily reliant on rainfall and other weather variables. It is such the
case that at times, farmers do not acquire the expected harvest due to the scarcity or abundance
of rainfall and other weather parameters. Climate change has a great impact on the productivity
of agriculture and may lead to hunger or food insecurity. The latter is a crucial problem in the
regions characterized by droughts or other weather-related disasters. Climate variables that affect
crop production include precipitation, air temperature, humidity, and solar radiation. Different
studies have shown that climate indices at both global and regional levels affect crop yields and
food security. In their study, Damien et al. found that the reduced crop yields could be associated
with either high temperature or abundant precipitation. Extreme temperature has negative effects
on crop production due to various factors such as increased evapotranspiration and respiration of
crops, and higher pest infestation. Increased precipitation intensity leads to increased runoff
patterns that in turn cause floods and the risk of crop failure. Crop productivity can also be
affected by the increased temperature that causes the increase in crop water demand. In all
scenarios, climate change has a potential impact on agriculture in different ways. Although the
climate variables may be the same for a specific area, however, the needs of weather parameters
are different from one crop to another according to their growing stage. This means that each
crop has a different level of resilience to the atmospheric variables. When weather variables
spike at an extreme level, a remarkable influence on crop production will be observed (2003).
The influence of climate change on agriculture can be observed everywhere. For example, from
March to August 2018, a large portion of Europe experienced extreme temperatures, while the
southern region of the continent experienced abundant rainfall (2005). In the context of
Maiduguri, climate change and its impacts on agriculture have been a challenge to the country in
some provinces that have faced long dry season or high rainfall. In 2016, the drought left 44,000
poor households food insecure in the eastern province between 2012 and 2016, landslides,
floods, and erosion harmed agriculture production in areas with steep slopes and heavy rainfall,
resulting in a 1.4% loss of Gross Domestic Product (GDP). According to the assessment carried
out by the Ministry of Agriculture and Animal Resources (MINAGRI), more than 3000 families
in the Eastern Province (Kayonza, Kirehe, and Nyagatare districts) faced hunger due to the
drought in (2017). The analysis of the variability in rainfall shows that rainy seasons tend to be
shorter with higher intensity and that tendency has an impact on crop yields due to droughts,
landslides, and floods. In its seasonal agriculture survey, the National Institute of Statistics of
Maiduguri (NISM) indicated that insufficient rainfall is the biggest factor that has a high
contribution to the bad harvest in Rwanda. In addition, the annual reports published by this
institution indicate that the seasonal harvest varies from one crop to another in the respective
agriculture seasons depending on the various circumstances including weather conditions. In
order to overcome the problems related to the variation of weather conditions on crops, various
solutions have been proposed in different studies. The investigation conducted by Safieh et al.
indicated that climate change has the impact on the crop water requirements as well as the
predicted crop yields in the future based on weather forecast data (2017). The study conducted
on the impact of extreme weather conditions on the different regions of Europe showed that the
most reliable weather predictors of agricultural production are rainfall and air temperature and
their respective thresholds. Precipitation and air temperature are the most common climatic
parameters used in many studies. However, other parameters such as solar radiation, air
humidity, soil moisture, and wind speed have been used to predict crop yields using different
machine learning models (MLM) such as the Artificial Neural Network (ANN), Semi parametric
Neural Network (2013), Convolutional Neural Network (CNN) (2014,2015), Lasso, Kernel
Ridge, Enet (2016), Naïve Bayes, K-Nearest Neighbor (2017), Recurrent Neural Network
(RNN), Long short-term memory (LSTM) (2018), and Random Forest (2017,2019). In
Maiduguri, various studies have been carried out with focus on predicting yields of different
crops. In (2020), Rugimbana applied the Aqua Crop model to predict maize yields under rainfed
agriculture in Eastern province of Rwanda. The author carried out a trend analysis on climatic
parameters such as maximum and minimum temperatures, rainfall, evapotranspiration and maize
yield. Among the findings was that rainfall trend had non-significant impact on yield over the
study area within the considered study period.

1.2 Statement of the Problem

Crop yield varies from year to year making crop management difficult and affecting food
security. This research aims to find the factors that affect the production of staple crops in
regions with deserted and semi-arid climate in Maiduguri and predict their yield.

1.3 Aim and Objectives of the Study

It aims to address food security challenges as well as provide a ground for which farmers and
policy makers could use to make informed decisions related to field operations, crop and
resource management, import and export strategies, and crop prices.

The objectives of this project are:

 a) To identify the environmental and economic factors that affect crop yield in the selected
region.
b) To build a predictive model that will estimate the yield of staple crops in a specific
country in the selected region using the identified factors.

1.4 Significance of the study

This project when completed have the ability to harness data-driven insight to optimize
agricultural practice, improve decision making, and ultimately enhance food production and
security in the region.

2.0 Related Works

Several works have been done in the field of machine learning for predicting crop yield .
Virendra Panpatil et al (2011) had made huge work for Indian farms by building profitable
yield recommendation schema. The planned schema is used find the best season for planting,
advancement of plant and Plant fulfillment. They used discrete classifier for generating better
correctness for occurrence. The best agreeable area of framework that it can without much of
an extent all-around all things be used to check on various yields.
Mayank et al (2012) created improvised schema for crop yield using executed AI
computations and with target to give effortless to use User Interface, rise the exactness of
crop yield estimate, examining discrete climatic parameters.
Zhihao et al (2013) two relapse administered AI strategies SVM, RVM to show viability in
soil quality forecast. A shrewd remote gadget for detecting soil dampness and meteorological
information.
Sabri Arik et al (2014) includes an analysis regarding Soil Fertility, Plant Nutrient by
utilizing back spread computation. The outcomes are exact and empowers advancement in
soil properties. It works best when contrasted with conventional techniques. Be that as it may,
framework is moderate wasteful and not steady.
Shivnath et al (2015) proposed about BPN to assess the test informational collection. BPN
utilizes a concealed layer which supports in better execution in foreseeing soil properties.
BPN present, is utilized to build up a self-prepared capacity to foresee soil properties with
boundaries. This results in more exactness and executes better compared to the customarily
utilized strategies, in any case, at times the framework turns be moderate and irregularity is
found in the yield.
Raval et al (2016) examine regarding the Knowledge Discovery Process and the rudiments of
different Data Mining approaches, for example, Association rules, Classification etc.,
Agrawal et al examine regarding different Data Mining devices, for example, Dashboards,
Text-Mining instruments. They give an outline about these apparatuses and the different
situations where they can be conveyed.
Grajales et al (2017) recommended a web app that uses open data set like verifiable creation,
land cover, nearby environment surroundings and coordinates them to give simple admittance
to the ranchers. The suggested engineering basically centers around open-source devices for
the advancement of the application. The client can choose area for which the subtleties are
accessible at a single tick.
Bendre et al (2018) gathers information about GIS, GPS, VRT and RS are controlled utilizing
Map Reduce calculation and direct relapse calculation to figure the climate information that
can be utilized in accuracy agribusiness.
Verma, A. et al (2019) used classification techniques for crop prediction like Naïve Bayes,
KNN algorithm on soil datasets which consists of nutrients of soil like zinc, Phosphorous,
copper, pH, iron, Sulphur, manganese, Organic Carbon, nitrogen, and potassium
Chakrabarty, A. et al (2010) made crop prediction in Bangladesh. They considered
parameters like soil composition, type of fertilizer, type of soil and its structure, soil
consistency, reaction and texture.
2.0 Methodology
The methodology employed in conducting the research on "Machine learning for predicting
crop yield in Maiduguri." Machine learning mainly consists of three learning methods,
namely supervised learning methods of training a model, supervised learning is a learning
method maps known input and output which maps from input to output. But in case in this
learning we should train the model in order to get desired output.
 Figure 1: System Architecture
4.0 Expected Results
The expected result of using machine learning for predicting crop yield in Maiduguri is to
optimize agricultural practice, enhance decision making and ultimately increase productivity
and resilience in the agricultural sector. With a user-friendly interface, users can seamlessly
navigate between functionalities.
5.0 Work Plan/Time Frame/ GANTT Chart
Feb-24 Mar-24 Apr-24 May-24 Jun-24 Jul-24 Aug-24 Sep-24

Preliminary
Survey

Data
Collection
and Pre-
processing

Literature
Review

Coding,
Model
Developme
nt, Testing
and
 Evaluation

Project
Report and
Submission

Bibliography
Shakoor, U.; Saboor, A.; Ali, I.; Mohsin, A.Q. Impact of climate change on agriculture:
Empirical evidence from arid region, Pakistan. J. Agric. Sci. 2011, 48, 327–333.
Molden, D.; Vithanage, M.; de Fraiture, C.; Faures, J.M.; Gordon, L.; Molle, F.; Peden, D.
Water Availability and Its Use in Agriculture. Treatise Water Sci. 2011, 4, 707–732.
Keen, B.A. Weather and crops. Q. J. R. Meteorol. Soc. 1940, 66, 155–166
Javadinejad, S.; Eslamian, S.; Askari, K.O.A. The analysis of the most important climatic
parameters affecting performance of crop variability in a changing climate. Int. J.
Hydrol. Sci. Technol. 2021
Beillouin, D.; Schauberger, B.; Bastos, A.; Ciais, P.; Makowski, D. Impact of extreme
weather conditions on European crop production in 2018: Random forest—Yield
anomalies. Philos. Trans. R. Soc. B Biol. Sci. 2020,
Uleberg, E.; Hanssen-Bauer, I.; van Oort, B.; Dalmannsdottir, S. Impact of climate change on
agriculture in Northern Norway and potential strategies for adaptation. Clim. Change
2014.
Mayank Champaneri, Chaitanya Chandvidkar, Darpan Chachpara, Mansing Rathod, “Crop
Yield prediction using machine learning” International Journal of Science and
Research, April 2020.
Pavan Patil, Virendra Panpatil, Prof. Shrikant Kokate, “Crop Prediction System using
Machine
Learning Algorithms”, International Research Journal of Engineering and
Technology, Feb 2020.
Raval Agrawal, H., Agrawal, P., “Review on Data Mining Tools”, International Journal of
Innovative Science, Engineering & Technology, Vol. 1, Issue 2, pp.52-56, 2014.
Sabri Arik, Tingwen Huang, Weng Kin Lai, Qingshan Liu , “Soil Property Prediction: An
Extreme Learning Machine Approach” Springer, vol. 3, Issue 4,666-680, 2015.
Shivnath Ghosh,Santanu Koley, “Machine Learning for Soil Fertility and Plant Nutrient and
Management using Back Propagation Neural Networks” IJRITCC, vol. 2, Issue 2,292-
297,2014.
Tan, L., “Cloud-based Decision Support and Automation for Precision Agriculture in Orchards”,
ScienceDirect, pp. 330-335, IFAC–Papers OnLine 49-16, pp.330-335, 2016
Zhihao Hong,Z. Kalbarczyk,R. K. Iyer, “A Data-Driven Approach to Soil Moisture Collection
and
Prediction” IEEE Xplore,vol. 2, Issue 2,292-297,2016.