Soil Analyzer and Plant Suggestion

RRL

Local:

SoilMATTic: Arduino-Based Automated Soil

Nutrient and pH Level Analyzer using Digital
Image Processing and Artificial Neural Network

Ricardo ALASCO, Eden Alyzza DOMDOMA, Karl Angelo DORIA, Kathleen Mae RICAFRANCA,
Yashmine Erika SAITO, Nilo ARAGO, Ryan REYES, Edgar Galido

2018 IEEE 10th International Conference on Humanoid, Nanotechnology, Information Technology,

Communication and Control, Environment and Management (HNICEM), 1-5, 2018

Gervacio, francisco et al., 2016., Soil analysis using ekeik

SoilMATTic was developed for faster and accurate soil analysis compared with conventional method to guide
farmers on crop suitability and increase farm productivity and crop yield. The Arduino-based prototype
automated the whole process of macronutrient and pH analysis of soil from soil testing procedures up to
fertilizer recommendation. It includes stepper motors and pumps to fully automate the chemical reaction of soil
with chemical reagent during testing and an on board printer to print out fertilizer recommendations. It uses
digital image processing technique to efficiently identify (1) Nitrogen, (2) Phosphorus, (3) Potassium and (4)
pH level of Philippine farmlands. The system is composed of five stages namely: automated soil testing, image
acquisition, image processing, training system, and recommendation. Artificial Neural Network offered fast
and accurate performance for the image processing. The system data base stored and manages 356 captured
images where 70% is for training, 15% for testing and 15% for balidation. Results of this this study showed
96.67 accuracy in identifying soil macronutrient and pH level and gives fertilizer recommendation for Inbred
rice plant, Inbred corn, Tobacco, sugarcane, Pineapple, Mango, Coconut, Abaca, Coffee, banana through a
generated report in printed form.

R. ALASCO et al., "SoilMATTic: Arduino-Based Automated Soil Nutrient and pH Level Analyzer using
Digital Image Processing and Artificial Neural Network," 2018 IEEE 10th International Conference on
Humanoid, Nanotechnology, Information Technology,Communication and Control, Environment and
Management (HNICEM), Baguio City, Philippines, 2018, pp. 1-5.
doi: 10.1109/HNICEM.2018.8666264
keywords: {Soil;Testing;Fertilizers;Nitrogen;Potassium;Soil;Arduino;Digital Image Processing;Artificial
Neural Network},
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8666264&isnumber=8666226

SoilMATe: Soil macronutrients and pH level assessment for rice plant through digital image processing using
artificial neural network

Nilo M Arago, John William F Orillo, Jenskie Jerlin Haban, Jomer Juan, John Carlo Puno, Jay Fel Quijano,
Gian Matthew Tuazon
Journal of Telecommunication, Electronic and Computer Engineering (JTEC) 9 (2-5), 145-149, 2017
https://journal.utem.edu.my/index.php/jtec/article/view/2415

In this study, digital image processing technique was used to efficiently identify the Macronutrients and pH
level of Soil in the farmland of Philippines:(1) Nitrogen,(2) Phosphorus,(3) Potassium and (4) pH. The
composition of the system is made of four sections namely, image acquisition, image processing, training
system, and result. The Artificial neural network was applied in this study for its features that make it well
suited in offering fast and accurate performance for the image processing. The system will base on 448
captured image data, 70% for training, 15% for testing and 15% for validation. Based on the result, the
program will generate a report in printed form. Overall, this study identifies the soil macronutrient and pH
level of the soil and gives fertilizer recommendation for inbred rice plant and was proven 98.33% accurate.

Arago, Nilo et al., SoilMATe: Soil Macronutrients and pH Level Assessment for Rice Plant through Digital
Image Processing Using Artificial Neural Network

Determination of soil nutrients and pH level using image processing and artificial neural network

John Carlo Puno, Edwin Sybingco, Elmer Dadios, Ira Valenzuela, Joel Cuello

2017 IEEE 9th International Conference on Humanoid, Nanotechnology, Information Technology,

Communication and Control, Environment and Management (HNICEM), 1-6, 2017

In this study, image processing and artificial neural network was used to efficiently identify the nutrients and
pH level of soil with the use of Soil Test Kit (STK) and Rapid Soil Testing (RST) of the Bureau of Soils and
Water Management: (1) pH, (2) Nitrogen, (3) Phosphorus, (4) Potassium, (5) Zinc, (6) Calcium, and (7)
Magnesium. The composition of the system is made of five sections namely soil testing, image capturing,
image processing, training system for neural network, and result. The use of Artificial Neural Network is to
hasten the performance of image processing in giving accurate result. The system will base on captured image
data, 70% for training, 15% for testing and 15% for validation as default of neural network tool of MATLAB.
Based on the result, the program will show the qualitative level of soil nutrients and pH. Overall, this study
identifies the soil nutrient and pH level of the soil and was proven accurate.

J. C. Puno, E. Sybingco, E. Dadios, I. Valenzuela and J. Cuello, "Determination of soil nutrients and pH level
using image processing and artificial neural network," 2017IEEE 9th International Conference on Humanoid,
Nanotechnology, Information Technology, Communication and Control, Environment and Management
(HNICEM), Manila, Philippines, 2017, pp. 1-6.
doi: 10.1109/HNICEM.2017.8269472
keywords: {Soil;Testing;Image processing;Zinc;Training;Nitrogen;Potassium;Soil;Digital Image
Processing;Artificial Neural Network;MATLAB;Nutrients},
URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8269472&isnumber=8268899

International

Soil Classification & Crop Suggestion based on

HSV, GLCM, Gabor Wavelet Techniques and
Decision Tree Classifier in Image Processing
T. Abimala, S. Flora Sashya and K. Sripriya

https://mail.easychair.org/publications/preprint_download/5gZm

Abstract- This paper is intended to support agriculture by classifying 7 different types of soils like Clay,
Clayey Peat, Clayey Sand, Humus Clay, Peat, Sandy Clay and Silty Sand, and in suggesting suitable crops that
could be grown in those particular soils using image processing. Pre-processing is done by using Low Pass
filter. HSV, GLCM, Gabor Wavelet algorithms are used for feature extraction. HSV, GLCM are
used to perform colour based feature extraction. Gabor filters are used to perform texture based feature
extraction. The features obtained from the test image are then compared with the features obtained from the
images in the dataset. Matching of image features is achieved by training the Decision Tree classifier with
statistical measurements like mean, standard deviation, skew and kurtosis. Finally the soil is predicted with
the help of segmented images that are given as input for simulation using Matlab R2018a and is followed by
crop
suggestion.

Ⅵ. CONCLUSION
The proposed system has added features like crop suggestion, prediction of water absorption by plants which
couldn’t be found in existing systems. Accuracy is more because feature
extraction is based on colour and texture of the input images. Thus our proposed idea will make sure to help
farmers, agriculture activists in efficient soil classification and crop suggestion.

Soil Test Based Smart Agriculture Management System

Ganesh Babu Rajendran

Chellaswamy Chellaiah
T.S.Geetha
T.Daniel Raj

IEEE International Conference on Smart Structures and Systems (ICSSS 2020)At: Chennai, India

https://www.researchgate.net/publication/345127195_Soil_Test_Based_Smart_Agriculture_Management_Syst
em

The estimation of crop based on the soil is essential nowadays for increasing the yield. In this paper, a soil-
based crop selection and fertilizer management system has developed and a normalized approach to
characterize the composition of bare soil, metalloids, and mesological parameters. From the statistical analysis,
we collect the data for various soils and which crop is suitable for cultivation to produce maximum yield for a
particular field. Various sensors, such as humidity sensor, temperature, and camera, are used to control and
monitor the agriculture field. In this study, the area around Tanjavur, Tamilnadu has been considered for the
crop selection of that area. Irrigation is controlled by water level sensors, GSM, and a controller. An APP has
developed to identify a suitable crop for the agriculture area, and it can easily install in the farmer's mobile
phone itself. Simulation has done using Matlab for four different crops. The results indicate that the proper
utilization of fertilizers protects the agricultural field and increases productivity. An experimental setup is
developed and tested under different test conditions.

Rajendran, Ganesh Babu & Chellaiah, Chellaswamy & T.S.Geetha, & Raj, T.Daniel & Venkatachalam, K. &
M.A.Mulla,. (2020). Soil Test Based Smart Agriculture Management System.
10.1109/ICSSS49621.2020.9202313.
IoT-Based Soil Health Monitoring and Recommendation System

Soil is the base of agriculture. Soil provides nutrients that increase the growth of a crop. Some chemical and
physical properties of soil, such as its moisture, temperature and its pH, heavily affect the yield of a crop.
These properties can be sensed by the open-source hardware, and they can be used in the field. In this chapter,
a soil health monitoring system is proposed in which farmer will be able to monitor soil moisture, soil
temperature and soil pH in his android smart-phone. The farmer will also get the recommendations of lime and
sulphur on the basis of pH of the soil. The area of study is Jaipur, Rajasthan (26.9124° N, 75.7873° E). The
proposed system is tested with the results taken from authorized laboratories. The proposed system is validated
with t-test having no significance difference between calibrated values and laboratory-recorded values. The
proposed system is implemented on android smart-phone so it is useful for farmers, agriculture scientists,
agriculture professionals and IoT experts.

Cite this chapter as:

Bhatnagar V., Chandra R. (2020) IoT-Based Soil Health Monitoring and Recommendation System. In:
Pattnaik P., Kumar R., Pal S. (eds) Internet of Things and Analytics for Agriculture, Volume 2. Studies in Big
Data, vol 67. Springer, Singapore. https://doi.org/10.1007/978-981-15-0663-5_1

First Online
25 October 2019
DOI
https://doi.org/10.1007/978-981-15-0663-5_1
Publisher Name
Springer, Singapore
Print ISBN
978-981-15-0662-8
Online ISBN
978-981-15-0663-5

Soil Monitoring and Testing Using IoT for Fertility Level and Crop Prediction

Agribusiness is the foundation of India. In India 50 % of the remaining task at hand depends upon
agribusiness. Commitment of agriculture part in Indian economy is higher than some other division in India. In
any case, Farmers utilized customary strategy for developing harvests which comes to less profitability of
yields. Additionally, a soil erosion and disintegration is likewise a principle motivation to less profitability of
yields. This will impact in diminishes fruitfulness level. Loss of soil supplements through different courses is
likewise motivation to diminish soil richness level. The supplements like potassium (K), nitrogen (N) and
phosphorus (P) are basic for the development of a plant. The advancement in agriculture is important to tackle
these issues in agribusiness part and shrewd cultivating is the appropriate response. This can be conceivable
utilizing IoT gadgets. Farmers can get the necessary data just as the screen is yield. IoT associates the entire
world with the assistance of sensors and other installed gadgets. The diverse soil tests will be taken from
various fields and soil esteems will be determined to utilize a PH sensor where supplements worth will be
separated from it. At that point, live information will be sent to the cloud database where information will be
put away. At that point dependent on information or data it will be broken down lastly we show signs of
improving crop yield. Here for information broke down information mining method is utilized. Information
mining in agriculture assumes an imperative job in yield expectation, soil fruitfulness and plant illnesses and so
on. Farmers can screen information on versatile by a website. What's more, farmers will likewise get crop list
dependent on that information which harvests will be conceivable to yield in that soil.

Raut, Swapnil and Chitre, Vidya, Soil Monitoring and Testing Using IoT for Fertility Level and Crop
Prediction (April 8, 2020). Proceedings of the 3rd International Conference on Advances in Science &
 Technology (ICAST) 2020, Available at SSRN: https://ssrn.com/abstract=3561682 or
http://dx.doi.org/10.2139/ssrn.3561682

Manso Rodríguez, R. A., & Machado Rivero, M. O. [3] proposed a paper entitled

Abdullah et al., [7] produced an experimental study entitled

arker, K. R., Attridge, E., Bennett, J., Hiserman, T., Horne, A. S., Moody, D.,
Vaughn, P. [9] introduced a paper entitled

Iranna M Shettar [10] designed a project namely

Ramsden A, Jordan L. [12] displayed a paper entitled Are students ready for QR
code

Ajay Shanker Mishra, Sachin Kumar Umre, Pavan Kumar Gupta [13] present a
project entitled

University in Poznan Kane, D., & Schneidewind, J. [11] introduced a paper entit-
led

Lo, L., Coleman, J., & Theiss, D. [2] proposed an survey entitled Putting QR
codes to the Test.

Title/Author Analysis Objectives of the Technique Rationale

Study Used in the
Study

Alasco, Ricardo et It uses digital image processing SoilMATTic was Digital Image Artificial Neural Network
al., 2018., technique to efficiently identify developed for faster and Processing offered fast and accurate
SoilMATTic: (1) Nitrogen, (2) Phosphorus, (3) accurate soil analysis and Artificial performance for the image
Arduino-Based Potassium and (4) pH level of compared with Neural processing. The system data base
Automated Soil Philippine farmlands. The system conventional method to Network stored and manages 356 captured
Nutrient and pH is composed of five stages guide farmers on crop images where 70% is for
Level Analyzer namely: automated soil testing, suitability and increase training, 15% for testing and
using Digital image acquisition, image farm productivity and 15% for validation. Results of
Image Processing processing, training system, and crop yield. The this this study showed 96.67
and Artificial recommendation. Arduino-based accuracy in identifying soil
Neural Network prototype automated the macronutrient and pH level and
whole process of gives fertilizer recommendation
macronutrient and pH for Inbred rice plant, Inbred corn,
analysis of soil from Tobacco, sugarcane, Pineapple,
soil testing procedures Mango, Coconut, Abaca, Coffee,
up to fertilizer banana through a generated
recommendation. It report in printed form.
includes stepper motors
and pumps to fully
automate the chemical
reaction of soil with
chemical reagent during
 testing and an on board
printer to print out
fertilizer
recommendations.
This study aimed to
further develop the
conventional soil
testing by automating
the whole process.
The chemical testing
on the soil is to be
done by an automated
machine using gear
motor and pumps
controlled by the
Arduino.

Arago, Nilo et al.,

SoilMATe: Soil
Macronutrients
and pH Level
Assessment for
Rice Plant through
Digital Image
Processing Using
Artificial Neural
Network

The Philippines is still predominantly an agricultural country despite many of its agrarian and rural
regions are transforming into industrial and urban societies and many croplands are being diverted to
other uses. Many Filipinos living in rural areas still support themselves through agriculture. According
Nations Encyclopedia, the country is producing and exporting its main agricultural crops such as rice,
corn, coconut, sugarcane, banana, pineapple, mango, abaca, coffee and tobacco [1]. The very high
dependency of Filipino farmers on cropland and the growing demand for food supply leads to soil
exhaustion. This means that ceaseless cultivation of food crops will render the soil deficient in important
macro and micronutrients, including nitrogen, phosphorous, potassium, sulphur, zinc, iron, bronze and
boron. According the Bureau of Soil and Water Management of the Department of Agriculture, it is
advised to get farmland soil analysed every three-years in order to combat any nutrient deficiencies by
applying organic or non-organic fertilizers and help maintain a soil ready farm for each planting season.
In this study, digital image processing technique was used to efficiently identify the Macronutrients and pH
level of Soil in the farmland of Philippines:(1) Nitrogen,(2) Phosphorus,(3) Potassium and (4) pH. The
composition of the system is made of four sections namely, image acquisition, image processing, training
system, and result. The Artificial neural network was applied in this study for its features that make it well
suited in offering fast and accurate performance for the image processing. The system will base on 448
captured image data, 70% for training, 15% for testing and 15% for validation. Based on the result, the
program will generate a report in printed form. Overall, this study identifies the soil macronutrient and pH
level of the soil and gives fertilizer recommendation for inbred rice plant and was proven 98.33% accurate.