Artificial Intelligence In Agriculture: Crop Disease Detection And Monitoring Plants

International Research Journal of Engineering and Technology (IRJET) e-ISSN:2395-0056

Volume: 09 Issue: 08 | Aug 2022 www.irjet.net p-ISSN:2395-0072

Artificial Intelligence In Agriculture: Crop Disease Detection And Monitoring Plants

4 1 2,3 U.G Student, Department of Information Technology Engineering, IITE, Ahmedabad, Gujarat, India 4Assistant Professor, Dept. of Computer Engineering, IITE, Ahmedabad, Gujarat, India ***

Abstract - Artificial intelligence is having a significant influence across all industries. By limiting environmental deterioration, AI was able to solve a variety of issues while also protecting a valuable resource. In terms of agricultural output, India ranks second. Each crop is susceptible to certain diseases, which have an impact on yield quantity and quality. Crop diseases account for roughly 42% of crop failure for most of the major food crops. Crop diseases tend to wipe out an entire crop's productivity. Early illness detection will allow for more efficient monitoring and good crop product.

This article offers a thorough review of an AI-based strategy for detecting and monitoring pest-infested crops and leaves. We share our research on crop disease detection and crop health using image processing, sensors, and other techniques in this publication. When it comes to assessing crops, the suggested method saves time and yields more precise results. In addition, we mentioned the destiny of AI-Powered agriculture and the realistic and technical demanding situations ahead. This survey will provide a clean concept approximately the present AI-Powered agriculture gadget and could assist researchers to broaden a brand-new ecosystem.

Key Words: Agriculture, Artificial intelligence, Disease Detection,CNN,Imageprocessing,Sensors

1.INTRODUCTION

At present, approximately 37.7% of the overall land floor is used for crop manufacturing, from the employment era to contribute to National Income, agriculture is crucial. With its rapid clinical growth and high-quality application location, Artificial Intelligence (AI) is one of the most popular subjects in software program engineering. The essential concept of AI in agriculture is its adaptability, rapid performance, precision, and cost-viability. Artificial Intelligence in Agriculture now no longer handiest allows farmers to apply their farming abilities however additionallyshiftstodirectfarmingtogetbetteryieldsand

higher fines with much fewer assets. AI enhances performance in crop harvesting, irrigation, soil content material sensitivity, crop monitoring, weed, harvest, and establishment. AI era allows diagnosis of plant diseases, pests, and malnutrition on farms, and AI sensors can hit uponandbecomeawareofweeds.

Hereinthispaper,wepresentanAI-basedtechniquefor detecting pest-infected crops and leaves in this paper. When it comes to assessing crops, the proposed method saves time and yields more exact results. Crop photographsareusedtocategorizethem.

Figure 1: ArtificialIntelligenceusesinAgriculture, Accessed16April2022.

2. AI Techniques Used for Detection of Diseases in Agriculture

2.1 Image Processing

A picture is turned into a numerical matrix that can be easily read by a computer to be processed. Picture enhancement, image restoration, image compression, and image analysis are just a few of the various forms of processing available. The latter is particularly intriguing sinceitallowspreciseinformationtobeextractedstraight froma picture.Theanalysiscanbe done bylookingatthe edges of images (image extraction), the colors of the images (texture analysis), and the motions identified as

Riya Patel1 , Kusum Meghrajani2 , Vaidehi Akhani3, Sejal Thakkar

International Research Journal of Engineering and Technology (IRJET) e-ISSN:2395-0056

Volume: 09 Issue: 08 | Aug 2022 www.irjet.net p-ISSN:2395-0072

they go from one image to the next. The procedure is brokendownintoafewfundamentalphases.

(a) Image Acquisition: -Imagesoftheinflamedleavesare obtained. This database has specific varieties of plant sicknesses, and the pics are saved in JPEG format. These picsarethenstudiedinMATLABwiththeuseofthestudy command.

(b) Image Pre-processing: Image pre-processing is used to erase noise from the photo or different item exclusion, specific pre-processing techniques. Image scaling is used to transform the authentic photo into thumbnails due to thefactthepixellengthoftheauthenticphotoishugeand it calls for greater time for the general system for this reason after changing the photo into thumbnails the pixel lengthgetslowerandit'sgoingtorequiremuchlesstime.

(c) Image segmentation: - Image segmentation is one of the maximum broadly used techniques to differentiate pixels of pics properly in a focused app. It distributes a photointoseveraldiscretestatessuchthatthepixelshave wonderful similarities in every region and excessive dissimilarityamongareas.

(d) Feature Extraction: - Feature Extraction is a critical part of illness detection. It plays a critical characteristic withinsidetheidentificationofanitem.Featureextraction is applied in numerous programs in photo processing. Color,textureedges,andmorphologyarethefeatures,that areappliedinsicknessdetection.

(e) Detection and classification of plant illnesses: -The final phases are the detection of diseases and the classification of plants with disease matches in the given datasetusingdiseaseclassifiers.

2.2 Convolutional Neural Network (CNN)

Usingbasicleafpicturesofhealthyandunwellplants,CNN models were built using deep learning methodologies to recognizeanddiagnoseplantillnesses.Thefirstusermust takeascreenshotoftheplantleaffromtheapp.Thisimage will be sent to our AI system via the application. Preprocessing, feature extraction, feature selection, and other processing stages are performed on the picture. CNN, a deep residue with 97.8% accuracy in recognizing four kinds of insects, was successfully trained using an innovative approach to constructing a visual database. Convolutional neural networks may accept data in any format, including audio, video, pictures, speech, and naturallanguage.

International Research Journal of Engineering and Technology (IRJET) e-ISSN:2395-0056

Volume: 09 Issue: 08 | Aug 2022 www.irjet.net p-ISSN:2395-0072

CNN is a type of deep, feed-forward artificial neural network(ANN)thathasbeeneffectivelyusedincomputer vision applications. CNN achieved great precision in the vast majority of the cases in which it was utilized, outperforming other prominent image-processing approaches.

ConvolutionalNeuralNetworksforthe AutomaticIdentificationofPlantDiseasesAccessed17 April2022

Figure 2:

International Research Journal of Engineering and Technology (IRJET) e-ISSN:2395-0056

Volume: 09 Issue: 08 | Aug 2022 www.irjet.net p-ISSN:2395-0072

2.3 Sensors

Agricultural sensors are sensors that are utilized in smart farming.Thesesensorsgiveinformationthathelpsfarmers monitor and optimize crops by allowing them to adjust to changesintheenvironment.Weatherstations,drones,and agricultural robots all have these sensors attached. They can be controlled using dedicated smartphone applications. They may be controlled directly through WiFiorviacellulartowersandoperatedusingmobilephones andalsousedinweatherstations.

Sensors in this system provide information on soil temperatureatnumerousdepths,airtemperature,rainfall, etc. They are employed in a variety of agro-based companies' equipment (e.g., dendrometers) for agricultural or farming purposes such as measuring trunk diameter, leaf wetness, and so on. In agriculture drones, they're utilized to spray insecticides and pesticides. Because of the lower cost of electricity, solar-powered mobilepumpshavebecomeincreasinglypopular.E-fences, whichassistprotectcropsfromanimalssuchaselephants, havebecomepopularinruralINDIA.

Fig 3: TypesofSensorsAccessed17April2022

Sr.no PaperTitle Publisher Year Outcome Link

1

ArtificialIntelligence (AI)inAgriculture IEEE 21May 2020

AnoutcomeonCropMonitoring,Data Science,DiseaseDetection,FoodQuality, PredictiveAnalytics

https://ieeexplore.ieee.org/ abstract/document/909801 1

2

ArtificialIntelligence inAgriculture Research Gate May 2018

Duringtheearly1980sand1990s,therulebasedwereextensivelyusedwhereasfrom 1990onwards,artificialneuralnetwork modelsandfuzzyinferencesystemshave takenthedominantrole.Inpresentyearsan uprisinguseofhybridsystemssuchas neuro-fuzzyorimageprocessingcoupled withartificialneuralnetworksisbeingused.

https://www.researchgate. net/profile/GouravmoyBanerjee/publication/3260 57794_Artificial_Intelligenc e_in_Agriculture_A_Literatur e_Ssurvey/links/5b35ab970 f7e9b0df5d83ec6/ArtificialIntelligence-in-AgricultureA-Literature-Survey.pdf

3

Multi-TaskCascaded Convolutional Networks IEEE

14-15 Feb 2020

Thedataresponsiblefortheplantgrowthis obtainedusingdifferentsensorunitslike DHT11,LDR,DS18B20,SoilMoisture sensors,Noircamera,single-board microcontrollers,andApplication ProgrammingInterfaces(APIs).

https://ieeexplore.ieee.org/ abstract/document/912289 4

4

International Research Journal of Engineering and Technology (IRJET) e-ISSN:2395-0056

Volume: 09 Issue: 08 | Aug 2022 www.irjet.net p-ISSN:2395-0072

5

ArtificialIntelligence Techniquesfor Agriculture Revolution:ASurvey Annalsof Rscb 2021

SmartSolutionfor LeafDiseaseand CropHealth Detection Springer May 2021

Thisarticlediscussesasystematicreviewof studiesanddescribesitslimitationsand strengths.Thisarticlepresentsdifferent applicationsofAI-Poweredsolutionsandthe productsavailableinthemarketfor providingservicestofarmers.Inaddition, wediscussedthefutureofAI-Powered agricultureandthepracticalandtechnical challengesahead

Thekeystepsthatweaddressedinthis paperareimagepre-processing,extraction offeatures,classification,andanalysisofthe resultsprovidedbythetechnique.

https://www.annalsofrscb.r o/index.php/journal/article /view/2796

https://link.springer.com/c hapter/10.1007/978-98116-0695-3_23

6

AI-basedDetectionof PestInfectedCrop andLeaf IEEE

13-14 May 2021

Imageprocessingmethodsareusedto analyzethecrops,furtherconvolutional neuralnetworksareappliedtodifferentiate thehealthycropsfromtheonesthatare infectedbysomediseaseandalsoshow somevisualremarks.

https://ieeexplore.ieee.org/ abstract/document/945169 8

7

PlantDisease Identificationusing ArtificialIntelligence: MachineLearning Approach

Internation al Journal of Innovative Research in Computer and Communica tion Engineerin g 14Jan 2021

Thefocalpointofprettymucheverynationhas moved towards the mechanization of agriculture to achieve exactness and precision and to serve the consistently expanding request for food. Among the significant difficulties in agriculture, plant disease detection is a critical factor influencing the result of cultivation The quality of vegetables, organic products, vegetables, and grains is influenced by plant disease, and hefty misfortune is underway, and therefore monetary losses are watched, so there is a prerequisite of quick and viable plant disease detectionandevaluationstrategies.Thispaper investigates the manners by which machine learningmodelscanbeappliedtoimprovethe cycle of plant disease detection in the beginning phases to improve grain security and manageability of the agro-biological system.

https://papers.ssrn.com/sol 3/papers.cfm?abstract_id=3 729753

8

ArtificialIntelligence toImprovetheFood andAgriculture Sector HINDAWI 22Apr 2021

Duetoseveralchallengesinthefuturefor theagricultureandfoodsectorandvarious factorssuchasclimatechange,population growth,technologicalprogress,andthestate ofnaturalresources(water,etc.),itisurgent

https://www.hindawi.com/ journals/jfq/2021/5584754 /

9

International Research Journal of Engineering and Technology (IRJET) e-ISSN:2395-0056 Volume: 09 Issue: 08 | Aug 2022 www.irjet.net p-ISSN:2395-0072

tousedigitaltechnologiesatdifferentstages oftheagriculturesupplychainsuchas automationoffarmmachinery,useof sensorsandremotesatellitedata,artificial intelligence,machinelearningforimproved monitoringoftooter,foragriculturefood producttraceability.

10

AI-BasedAutomatic CropDisease DetectionSystem IEEE

9-11 July 2021

ArtificialIntelligence andItsApplications inAgricultureWith theFutureofSmart Agriculture Techniques inglobal 2019

Themainaimofthisprojectistodesignan AI-Baseddiseasedetectionsystemthat detectsthetypeofdiseasepresentintomato leavesbyclickingtheimagesofvarious leavesthroughthecameraandsprayingthe respectivepesticideonthediseasedpartof theplant.

https://ieeexplore.ieee.org/ abstract/document/962270 0

includingsevensteps,namelycropselection, soilpreparation,seedselection,seedsowing, irrigation,cropgrowth,fertilizing,and harvesting;andhowthesedigital technologiesarehelpfulforthecropcycle

https://www.igiglobal.com/chapter/artificia l-intelligence-and-itsapplications-in-agriculturewith-the-future-of-smartagriculturetechniques/268026

11

Applicationof artificialintelligence techniquesin irrigationandcrop healthmanagement forcropyield enhancement ELSEVIER 2021

3. Conclusion

Toimprovethebasicrequirementofwater supplylevelandwaterfortheparticular cropatdifferentstagesofgrowthtopredict thewaterlevelrequirementandtheir performancescanbecompared.

The current review study covers the various applications ofartificial intelligenceinagriculture.The primarygoal of this research was to provide an overview of the uses and existingtechniquesofartificialintelligencetohelpfarmers achieve the desired output. The report also covers numerous pieces of literature that reflect various approaches to detecting agricultural diseases. In line with the literature, artificial intelligence is an extraordinary device for a country's agronomics. As a result, future researchers should compile a comprehensive dataset spanning all aspects of agriculture and improve present technologytoboostprimarysectorproduction.

https://www.sciencedirect. com/science/article/pii/S2 214785320378330

In this paper, a well-timed correct evaluation of plants is beingfinishedwiththeassistanceofImageProcessingand CNN. This can result in development withinside the agriculture field. Data Augmentation in this situation has provided super results for the model as it reduced the overfitting.

4. Future Scope

India's population is expected to acquire more than 1.6 billionthroughmannerofapproachof2030.Withthisbig hikeinthepopulace,you'llbeabletoanticipatealargecall for agricultural intake as well. With the development withinside the carrier zone, there may be a massive migrationofateamofworkersfromthenumberonezone

International Research Journal of Engineering and Technology (IRJET) e-ISSN:2395-0056

Volume: 09 Issue: 08 | Aug 2022 www.irjet.net p-ISSN:2395-0072

to the tertiary zone. In addition, the lack of awareness of growing illnesses in plants is lowering the yield of cultivation as well. Food being the primary necessity of human life, future researchers need to take the course for reviving the agriculture arena. Artificial Intelligence must be the foremost gear for the researchers to cope with the above-stated issues. With the exceptional variety in agronomy species, an in-depth database desires to be acquired for numerous quantities of agriculture. With the usage of the right gear of synthetic intelligence and with the right dataset, farming may be made greater green for farmers.Thesetechniquesmaybetakenintoconsideration because the foremost implementation is to clear up the destinycrisis.

References

[1] Revanth. (n.d.). Towards future farming: How artificial intelligence is transforming the Agriculture Industry. Wipro. Retrieved August 4, 2022, from https://www.wipro.com/holmes/towards-futurefarming-how-artificial-intelligence-istransforming-the-agriculture-industry/

[2] Boulent,J.,Foucher,S.,Théau,J.,&St-Charles,P.-L. (1AD, January 1). Convolutional neural networks for the automatic identification of plant diseases. Frontiers. Retrieved August 4, 2022, from https://www.frontiersin.org/articles/10.3389/fpl s.2019.00941/full

[3] Lakhiar,I.A.,Jianmin,G.,Syed,T.N.,Chandio,F.A., Buttar, N. A., & Qureshi, W. A. (2018, December 19). Monitoring and control systems in agricultureusingIntelligent SensorTechniques:A review of the aeroponic system. Journal of Sensors. Retrieved August 4, 2022, from https://www.hindawi.com/journals/js/2018/867 2769/

[4] Liu, S. Y. (2020). Artificial Intelligence (AI) in agriculture. IT Professional, 22(3), 14–15. https://doi.org/10.1109/mitp.2020.2986121

[5] International Journal of Scientific Research in Computer Science Applications and Management Studies. (2018, May). Artificial Intelligence in agriculture: A literature survey. Retrieved August 3, 2022, from https://www.researchgate.net/publication/3260

57794_Artificial_Intelligence_in_Agriculture_A_Lit erature_Survey

[6] Singh, R., Srivastava, S., & Mishra, R. (2020). AI and IOT-based monitoring system for increasing the yield in crop production. 2020 International Conference on Electrical and Electronics Engineering (ICE3). https://doi.org/10.1109/ice348803.2020.912289 4

[7] Dwari,A.,Tarasia,A.,Jena,A.,Sarkar,S.,Jena,S.K., & Sahoo, S. (2021). Smart solution for leaf disease and crop health detection. Lecture Notes in Networks and Systems, 231–241. https://doi.org/10.1007/978-981-16-0695-3_23

[8] Ahmed, M., Mahajan, T., Sharma, B. D., Kumar, M., & Singh, S. K. (2021). AI-based detection of Pestinfectedcropandleaf.20213rdInternational Conference on Signal Processing and Communication (ICPSC). https://doi.org/10.1109/icspc51351.2021.94516 98

[9] Kothari, Jubin Dipakkumar, Plant Disease IdentificationusingArtificialIntelligence:Machine Learning Approach (2018). Jubin Dipakkumar Kothari (2018). Plant Disease Identification using Artificial Intelligence: Machine Learning Approach. International Journal of Innovative Research in Computer and Communication Engineering, 7(11), 11082-11085., Available at SSRN:https://ssrn.com/abstract=3729753

[10] S. N and J. S, "AI-Based Automatic Crop Disease Detection System," 2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONNECT), 2021, pp. 1-6, DOI: 10.1109/CONECCT52877.2021.9622700.

Turn static files into dynamic content formats.

Create a flipbook