Revolutionizing and Agriculture Farming Through Artificial Intelligence

Revolutionizing and Agriculture Farming Through Artificial Intelligence

Budhesh Pratap Singh¹ , A. Krishnamoorthi² , Vijay Kumar³ , P. Kalaiselvi⁴

¹Department of Vegetable Science, Chandra Shekhar Azad University of Ag and Technology, Kanpur, U.P., 208002, India

²ICAR-National Bureau of Plant Genetic Resources-Pusa campus, IARI New Delhi -110012, India

³Indian Council of Agricultural Research - Sugarcane Breeding institute, Regional Centre, Karnal-132001, India

⁴ICAR- Krishi Vigyan Kendra, Tamil Nadu Agricultural University, Salem, Tamil Nadu-India

Corresponding Author Email: krishnavivaan007@gmail.com

DOI : https://doi.org/10.51470/JOD.2024.03.01.13

Abstract

Keywords

Download this article as:

Introduction

The agricultural business, which is one of the most significant sectors for the economy and food supply, is undergoing a transformation as a result of the use of artificial intelligence (AI) and machine learning (ML). AI solutions are helping farmers to accomplish more with less, increase quality, and guarantee quicker go-to-market for crops [1]. This is particularly important in light of the fact that the world population is predicted to exceed 8.5 billion by the year 2030. Machine learning technology, which is a form of artificial intelligence that mimics human behaviour, has the potential to advance crop production in a variety of ways. These include the analysis of sensor data and historical trends to forecast crop yields, the forecasting of production costs, the recommendation of pesticides, the simplification of crop breeding, and the identification of plants, weeds, pests, and diseases. In addition to this, it is able to perform precise spraying to hyper-targeted regions, precisely applying the appropriate quantity of herbicide [2].
The use of cognitive computing in agriculture may aid in the learning, comprehension, and interaction with a variety of surroundings, hence increasing overall production. Farmers are able to proactively safeguard their crops, prevent loss, and preserve a bigger yield when they are able to plan for agricultural issues such as droughts, weather, or pollution. This is made possible by the use of prediction models, which provides the ability to foresee agricultural challenges [3].

The Internet of Things (IoT) and precision farming are two of the most prominent applications. Site-specific crop management (SSCM) is a strategy that uses automated seeders to guarantee effective output without draining the soil to an excessive degree. In addition, artificial intelligence sensors may be used for precision farming, which enables farmers to hyper-target weeds and pests in particular zones rather than treating the full range of crops. In this way, the use of chemicals, water, and other resources is maximized, resulting in the production of the most nutritious and abundant quantity of crops [5]. The use of drone photography for crop monitoring and field surveys is beneficial to farmers since it enables them to boost yields and provides them with real-time analytics and information. Drones have the capability to gather data from the air and employ sensors for monitoring and evaluation, therefore providing farmers with feedback that is interactive. AI may also be helpful in optimizing supply chains, which is another instance. AI has the potential to improve the supply chain, so enhancing logistics and transportation while simultaneously lowering waste. It has the ability to consolidate systems, which enables better accessibility and transparency amongst different distributors. Throughout the supply chain, real-time monitoring and updates make it possible to communicate and solve problems in a timely manner [6].

Artificial Intelligence in Agriculture

It is true that artificial intelligence has found several uses in agriculture, and there are countless instances of this in the actual world. The following are some examples of how artificial intelligence is having a huge impact:

1. Analysis of Data for Decisions Regarding Farming: Over the course of a single day, farms produce hundreds of thousands of data points. Farmers are now able to examine a number of things in real time with the use of artificial intelligence. These items include weather conditions, temperature, water consumption, and soil conditions obtained from their farm. This allows them to make choices that are more informed. For instance, artificial intelligence technologies assist farmers in optimizing their planning in order to create more abundant harvests. This is accomplished by selecting the optimum hybrid seed options, crop choices, and resource use [7].
2. Precision Agriculture: When it comes to harvesting, artificial intelligence technologies are helping to improve both the quality and accuracy of the crop. On farms, this method makes use of artificial intelligence technology to assist in the detection of illnesses in plants, pests, and inadequate plant nutrition. Using artificial intelligence sensors, weeds may be identified and targeted, and then the appropriate herbicides can be applied within the appropriate buffer zone [8]. This prevents the over application of herbicides and the accumulation of excessive toxins in our food.
   Agricultural farmers are using artificial intelligence to develop seasonal forecasting models in order to enhance the accuracy of agricultural forecasting and to boost agricultural production. In order to aid farmers in making choices, these models are able to forecast anticipated weather patterns months in advance. This is especially helpful for small farms in poor nations, where there may be a lack of data and information readily available [9,53].
3. In order to keep an eye on their crops, farmers are increasingly turning to drones for surveillance. In order to analyse the data that is collected by drones flying over agricultural fields, computer vision and deep learning algorithms are used. AI-enabled cameras may be mounted on drones to take pictures of the whole farm and then analyse those pictures in a manner that is very close to real time in order to pinpoint problem areas and possible areas for development [10].
4. Artificial Intelligence Agriculture Bots: As a result of fewer individuals joining the agricultural industry, the majority of farms are now dealing with the difficulty of a scarcity of workers. Artificial intelligence farm bots are one potential answer to the problem of a lack of manpower. These robots are able to harvest crops at a larger volume and quicker speed than human workers, detect and eradicate weeds with more accuracy, and cut expenses for farms by providing a labour force that is available around the clock so that they can work [11,52].
5. This set of instances demonstrates that artificial intelligence is not only a theoretical notion but rather a real instrument that is rapidly becoming the standard in the agricultural sector, so ushering in a new age of intelligent agriculture.
6.  

An Increase in the Use of Precision Agriculture

In the field of agriculture, the use of artificial intelligence to precision farming is making tremendous progress. This method makes use of artificial intelligence to assess data obtained from a variety of sources, including soil sensors, weather predictions, and satellite imaging, in order to deliver accurate suggestions for planting, fertilizing, and harvesting options. The following are some instances from the real world that highlight the influence that precision farming has have:

1. Developing and conducting research: A number of applications of machine learning, including deep learning, are now being used to identify data outliers or to match data against known patterns with an unparalleled level of accuracy and recall. As a consequence, the agricultural industry experiences a higher rate of innovation and a better degree of efficiency [12].
2. When applied to key phrases or research, artificial intelligence is being used to apply text analytics and natural language processing, which is significantly decreasing or eliminating the need for manual online and paper sorting. This allows for faster identification of research data. The procedure of locating research data that is valuable is simplified as a result of this [13].
3. AI is being utilized for intelligent automation, such as drones collecting photographs of crops so that the agricultural production may be calculated. This is a great example of how AI is being used to improve efficiency and effectiveness. This makes it possible to make more accurate estimates about yields and to allocate resources more effectively [14].
4. Drones and computer vision are being merged in order to provide quicker evaluations of field conditions and to prioritize integrated pest management techniques. This will allow for the early detection of pests, diseases, and weeds. The early diagnosis and management of potential hazards to crop health is made possible as a result of this.
   Data analytics, sensor technologies, the internet of things (IoT), machine learning, and cognitive computing are being used in precision agriculture in order to continuously monitor soil moisture, light, and humidity. This makes it possible to make modifications to agricultural operations in real time, which ultimately results in more optimal crop health and productivity [15].
5. The analysis of market demand may be made easier by artificial intelligence, which can also assist farmers in determining which types of product would provide the most profits based on the current market trends and demand projections [16].
6. Artificial intelligence gives farmers with forecasting and predictive analytics, which helps them lower the likelihood of crop failures and reduce the number of mistakes that occur. As a result, this contributes to improved planning and risk management.
   Weather Forecasting: Artificial intelligence gives farmers the ability to anticipate temperatures and estimate the amount of fruits and vegetables that will be harvested from a crop. Additionally, it may assist farmers in determining the most effective irrigation patterns depending on the anticipated rainfall [17, 51].
7.  

Practical application

Optimization of irrigation systems that are automated

Using AI algorithms, autonomous crop management is now possible. It is possible for algorithms to make decisions in real time about the amount of water that should be provided to crops when they are integrated with Internet of Things (IoT) sensors that monitor the levels of soil moisture and the meteorological conditions. The goal of an autonomous crop irrigation system is to reduce water use while simultaneously fostering environmentally responsible agricultural practices [18].

The Application of Artificial Intelligence in Agriculture:

The Future of Farming investigating irrigation systems for any signs of damage or leakage.
In irrigation systems, artificial intelligence plays a significant role in locating leaks. When algorithms examine data, they are able to recognize patterns and abnormalities that may signal the presence of possible leaks. It is possible to train machine learning (ML) models to detect certain leak signatures, such as variations in water flow or pressure. These signatures may be used to identify leaks. The use of real-time monitoring and analysis makes it possible to discover problems at an early stage, so minimizing water waste and potential harm to crops [19,50].
AI also takes into account meteorological data in addition to crop water needs in order to locate regions that have an excessive amount of water use. Artificial intelligence technology improves water efficiency via the automation of leak detection and the provision of notifications, therefore assisting farmers in conserving resources [20].
The monitoring of crops and soil
having the improper mix of nutrients in the soil may have a significant impact on the health of crops as well as their development. These nutrients may be identified and their impact on crop productivity can be determined with the use of artificial intelligence, which enables farmers to simply make the required modifications.
When it comes to gathering reliable data, human observation is not as precise as computer vision models, which can monitor soil conditions and collect accurate information. The information obtained from plant science is then used to ascertain the state of the crop, forecast the yields, and identify any specific problems that may exist.
It has been shown that artificial intelligence is capable of properly tracking the phases of wheat development and the maturity of tomatoes with a degree of speed and precision that cannot be matched by a person [22,49].
The Application of Artificial Intelligence in Agriculture: The Future of Farming
Infectious diseases and pests detection. In addition to determining the quality of the soil and the development of the crop, computer vision can also determine whether or not diseases or pests are present. Artificial intelligence is used to scan photos in order to identify mould, rot, insects, and other potential dangers to the health of crops. When used in combination with alarm systems, this enables farmers to take prompt action in order to eradicate pests or isolate crops in order to avoid the spread of disease [23]. With an accuracy of over 90 percent, artificial intelligence has been used to identify apple black rot. It is also capable of identifying insects such as flies, bees, moths, and other similar creatures with the same level of precision. On the other hand, in order to obtain the appropriate amount of the training data set to train the algorithm with, the researchers first needed to gather photos of these insects [24].
Observing the health of the animals
Even if it would seem to be simpler to identify health issues in animals than in crops, the reality is that it is a very difficult task. The good news is that AI can assist with this. As an example, a business known as CattleEye has created a system that employs drones, cameras, and computer vision in order to remotely monitor the health of cattle. It recognizes events such as birthing and identifies behavioural patterns that are not typical of cattle [25].
In order to identify the influence that nutrition and environmental circumstances have on cattle and to deliver significant insights, CattleEye employs artificial intelligence and machine learning technologies. With this information, farmers may enhance the health of their cattle, which will ultimately lead to an increase in milk output [26].
The Application of Artificial Intelligence in Agriculture: The Future of Farming
Farmers have a good understanding of the fact that the application of pesticides is ready to be optimized at this point. Unfortunately, there are significant restrictions associated with both the human and automated application procedures. When it comes to targeting particular locations, the application of pesticides manually gives better accuracy, despite the fact that it may be a long and laborious process still. Spraying pesticides using an automated system is more efficient and requires less manual effort, but it often lacks precision, which may lead to pollution of the environment [27].
Drones that are powered by artificial intelligence provide the finest benefits of each strategy while avoiding the limitations of each. For the purpose of determining the quantity of insecticide that should be sprayed on each area, drones make use of computer vision. This technology is constantly growing more precise, despite the fact that it is still in its infancy [28].
The Application of Artificial Intelligence in Agriculture: The Future of Farming
ML techniques are used in yield mapping in order to do real-time analysis on big datasets. This provides farmers with a greater understanding of the patterns and features of their crops, which in turn enables them to plan more effectively. Farmers are able to forecast the amount of soil yields that various crops will produce by integrating methods such as three-dimensional mapping, data from sensors, and drones. Multiple drone flights are used to gather data, which enables algorithms to be used to do analysis that is more exact.
It is possible to make an accurate forecast of future yields for certain crops using these approaches. This provides farmers with the ability to choose where and when to plant seeds, as well as how to distribute resources in order to get the highest possible return on investment [29].
Automatic harvesting and weeding of the crop
In the same way that computer vision can identify illnesses and pests, it can also be used to identify weeds and types of plants that are considered to be invasive. Computer vision, when paired with machine learning, examines the size, shape, and colour of leaves in order to differentiate between crops and weeds. The programming of robots that carry out activities that are part of robotic process automation (RPA), such as autonomous weeding, may be accomplished with the help of such technologies. In point of fact, exactly this kind of robot has previously been put to good use. As these technologies become more widely available, it is possible that smart bots may be able to do all of the tasks associated with agricultural harvesting and weeding [30].
Harvesting and sorting the crops
AI is not just helpful for recognizing possible problems with crops while they are growing; it also has other applications. It is also responsible for a function that occurs following the harvesting of the crop. In the past, the majority of sorting procedures were performed manually; however, artificial intelligence has the ability to sort output more correctly.
Computer vision has the ability to identify diseases and pests in crops that have been harvested. Not only that, but it is also able to classify product according to its size, shape, and colour. Because of this, farmers are able to easily divide their produce into several categories, which allows them to sell their products to a variety of clients at varying costs. Traditional manual sorting techniques, on the other hand, may be very labour-intensive throughout the whole process [31].
The Application of Artificial Intelligence in Agriculture: The Future of Farming

When it comes to farm management, security is an essential component. On account of the fact that it is difficult for farmers to keep a constant watch on their fields, farms are often targeted by thieves. The presence of animals poses a further risk, whether it be foxes who break into the chicken coop or the cattle of a farmer that cause damage to the crops or the machinery. Computer vision and machine learning have the potential to detect security breaches in a short amount of time when paired with video surveillance systems. While some systems are even sophisticated enough to differentiate between authorized visitors and staff, others are not [32].
AI’s function within the context of the information management cycle for agriculture
Utilizing AI to manage agricultural data might be advantageous in a variety of various ways:
Take control of risks
The use of predictive analytics helps make agricultural procedures less prone to mistakes.
Plant breeding artificial intelligence made use of data on plant development in order to provide more guidance on crops that are more resistant to adverse weather conditions, diseases, or pests [33].
Conducting a soil and crop health analysis
The chemical makeup of soil samples may be analysed by AI algorithms, which can use this information to detect which nutrients may be deficient. Additionally, AI is able to recognize and even anticipate agricultural illnesses.
The use of artificial intelligence in irrigation is beneficial for determining the ideal patterns and times for applying nutrients, as well as forecasting the optimal combination of agronomic goods [34].
Artificial intelligence that harvests crops is effective for increasing agricultural yields and can even determine the optimal time to harvest crops.
Developing software for agricultural purposes
Through the use of technology, field conditions can be monitored, irrigation can be optimized, and overall crop management may be improved.
Using artificial intelligence to improve agricultural practices and operations
While the advantages of artificial intelligence in agriculture are undeniable, it is impossible for it to work without other digital technologies that are already in place, such as software, sensors, and large amounts of data [35]. Artificial intelligence is also necessary for the correct operation of other technologies. In the case of large data, the data alone does not provide for especially relevant information. The way in which it is digested and executed is what is important.
Big data for the purpose of making informed decisions
With the help of artificial intelligence and big data analytics, farmers are able to get suggestions that are based on accurate and up-to-date information, which ultimately leads to an increase in production and a decrease in expenditures [36].
Using Internet of Things sensors to collect and analyse data
IoT sensors, in conjunction with other supporting technologies such as artificial intelligence drones, geographic information systems, and other tools, have the capability to monitor, measure, and store training data on a variety of variables in real time. With the help of artificial intelligence, farmers are able to receive precise information in a short amount of time [37].
Using robots and intelligent automation to reduce the amount of physical labour required
The prevalent issue of labour shortages may be helped to be solved by combining artificial intelligence with autonomous tractors and the internet of things. The usage of robotics is also significant; for example, agricultural robots are already being put to use to do manual chores such as picking crops. Formwork is a field in which robots are more beneficial than humans because of their capacity to work for extended periods of time, their increased accuracy, and their decreased likelihood of making mistakes [38].

The Prospects for Artificial Intelligence in Agriculture
While it is true that the achievements of artificial intelligence in agriculture have a great deal of promise, it is essential to recognize the difficulties that are yet to come. A multitude of intricate problems that need to be resolved in order to fully realize the promise of artificial intelligence in agriculture are connected with the future of AI in agriculture.

1. Concerns around Data Privacy: Agriculture, like any other industry that is largely dependent on data, is struggling with concerns around data privacy. There is a growing worry among farmers over the confidentiality of their data and the manner in which it is being used. A number of concerns have been raised about the possibility of rivals gaining access to data or using it to affect market pricing. For the purpose of preserving confidence and fostering the use of artificial intelligence in agriculture, it is essential to make certain that adequate data privacy and security safeguards are in place [39].
2. Divide in Digital Technology: Another key obstacle is the digital divide that exists between large-scale farms and small-scale farmers. Small-scale farmers may not have the means or the technical know-how to invest in sophisticated artificial intelligence technology, but large farms often have more resources available to invest in such technologies. On account of this mismatch, a competitive imbalance may occur, in which big farms are able to enjoy the advantages of artificial intelligence while small farms are left behind. For the purpose of ensuring that the advantages of artificial intelligence in agriculture are spread fairly, it is vital to bridge this digital gap [40].
3. The fast growth of artificial intelligence in agriculture has overtaken the establishment of standards and regulations, which has resulted in the need for crystal clear standards and rules. It is necessary to have clear criteria on the use of artificial intelligence, which should include ethical issues, accountability, and openness. It is possible that the advantages of artificial intelligence might be undermined if they are not there because there is a danger of abuse or unforeseen effects [41].
4. Despite the fact that artificial intelligence has the ability to lessen the negative effects that farming has on the environment by maximizing the use of resources, there are still worries over the environmental imprint that it leaves behind. As an example, the amount of energy that is used by data centres that are operating AI algorithms might be rather significant. There is a difficulty that has to be addressed, and that is finding a balance between the environmental advantages and drawbacks of automation [42].
5. Despite these obstacles, there is a tremendous amount of promise for artificial intelligence to assist agriculture. It is possible for artificial intelligence to boost agricultural yields, increase efficiency, decrease waste, and assist farmers in adapting to shifting environmental circumstances. It also has the potential to contribute to food security by assisting in the sustainable fulfilment of the ever-increasing demand for food on a global scale [43].
6. The trip toward the general use of artificial intelligence in agriculture may be filled with difficulties, but it is a one that is well worth doing. By tackling these difficulties head-on, we will be able to harness the potential of artificial intelligence to revolutionize agriculture and pave the way for a future in which farming is more environmentally friendly [44].

Challenges
AI solutions may be expensive, particularly for small-scale farmers and those in developing nations.

1. Large upfront costs: AI solutions can be expensive.
2. Farmers often exhibit resistance to embracing new technologies owing to a lack of experience with these technologies when they are introduced [45].
3. A lack of practical experience: Because the technical improvements in the agriculture business differ from country to country, it is difficult for technology firms to provide training and assistance to their employees [46,53].
4. A more drawn-out process for the adoption of technology: The agricultural industry does not have the infrastructure that is necessary for artificial intelligence to work, which makes it difficult for even existing farms to advance.
5. Limitations imposed by technology: Accurate models are dependent on a wide variety of high-quality data, which might be difficult to come by in the agricultural sector [47].
6.  Privacy and security concerns: There is a lack of legislation pertaining to the use of artificial intelligence across all sectors, which raises legal considerations concerning possible disruptions to food supply and potentially dangerous security risks [48].

Conclusion

In conclusion, the integration of Artificial Intelligence (AI) into agriculture marks a significant advancement with the potential to revolutionize the way we produce food, manage resources, and address global food security challenges. By leveraging AI-powered technologies such as precision agriculture, robotics, and predictive analytics, farmers can optimize crop yields, minimize resource usage, and mitigate environmental impact. The predictive capabilities of AI enable proactive decision-making, allowing farmers to anticipate challenges and adapt to changing conditions effectively. However, the widespread adoption of AI in agriculture requires addressing various challenges, including data privacy concerns, technological infrastructure limitations, and equitable access to AI tools. Moreover, ethical considerations regarding the responsible deployment of AI and its potential socio-economic impacts must be carefully addressed. Despite these challenges, the transformative potential of AI in agriculture is undeniable. With continued innovation, collaboration, and responsible stewardship, AI holds the promise of creating a more sustainable, resilient, and productive agricultural system for generations to come.

References

[1]. Abawi GS, Widmer TL (2000) Impact of soil health management practices on soilborne pathogens, nematodes and root diseases of vegetable crops. Appl Soil Ecol 15:37–47

[2]. Abdullahi HS, Mahieddine F, Sheriff RE (2015) Technology impact on agricultural productivity: A review of precision agriculture using unmanned aerial vehicles. In: Wireless and Satellite Systems: 7th International Conference, WiSATS 2015, Bradford, UK, July 6–7, 2015. Revised Selected Papers 7. Springer, pp 388–400
[3]. Aitkenhead MJ, McDonald AJS, Dawson JJ et al (2003) A novel method for training neural networks for time-series prediction in environmental systems. Ecol Model 162:87–95. https://doi.org/10.1016/S0304-3800(02)00401-5

[4]. Aryalekshmi BN, Biradar RC, Chandrasekar K, Ahamed JM (2021) Analysis of various surface energy balance models for evapotranspiration estimation using satellite data. Egypt J Remote Sens Sp Sci 24:1119–1126

[5]. Bilgili M (2011) The use of artificial neural networks for forecasting the monthly mean soil temperatures in Adana, Turkey. Turk J Agric For 35(1):83–93. https://doi.org/10.3906/tar-1001-593
[6]. Brazeau M (2018) Fighting weeds: can we reduce, or even eliminate, herbicides by utilizing robotics and AI. Genetic Literacy Project, North Wales

[7]. Chandel AK, Tewari VK, Kumar SP, et al (2018) On-the-go position sensing and controller predicated contact-type weed eradicator. Curr Sci 114:1485–1494. https://doi.org/10.18520/cs/v114/i07/1485-1494
[8]. Chang C-L, Lin K-M (2018) Smart agricultural machine with a computer vision-based weeding and variable-rate irrigation scheme. Robotics 7:38. https://doi.org/10.3390/robotics7030038

[9]. Dahikar SS, Rode SV (2014) Agricultural crop yield prediction using artificial neural network approach. Int J Innov Res Electr Electron Instrum Control Eng 2:683–686

[10]. Dai X, Huo Z, Wang H (2011) Simulation for response of crop yield to soil moisture and salinity with artificial neural network. Field Crops Res 121(3):441–449. https://doi.org/10.1016/j.fcr.2011.01.016
[11]. Datta A, Ullah H, Tursun N et al (2017) Managing weeds using crop competition in soybean [Glycine max (L.) Merr.]. Crop Prot 95:60–68
[12]. Dhanya VG, Subeesh A, Kushwaha NL, Vishwakarma DK, Kumar TN, Ritika G, Singh AN (2022) Deep learning based computer vision approaches for smart agricultural applications. Artif Intel Agric 6211–6229. https://doi.org/10.1016/j.aiia.2022.09.007
[13]. Dukes MD, Shedd M, Cardenas-Lailhacar B (2009) Smart irrigation controllers: how do soil moisture sensor (sms) irrigation controllers work? Univ Florida, Inst Food Agric Sci FL, USA, p 1

[14]. Dursun M, Ozden S (2011) A wireless application of drip irrigation automation supported by soil moisture sensors. Sci Res Essays 6:1573–1582

[15]. FAO (2017) Food and Agriculture Organization of the United Nations. The state of food and agriculture leveraging food systems for inclusive rural transformation. FAO, pp 1–181

[16]. Gandhi M, Kamdar J, Shah M (2020) Preprocessing of non-symmetrical images for edge detection. Augment Hum Res 5:1–10. https://doi.org/10.1007/s41133-0190030-5

[17]. Gebregiorgis MF, Savage MJ (2006) Determination of the timing and amount of irrigation of winter cover crops with the use of dielectric constant and capacitance soil water content profile methods. South African J Plant Soil 23:145–151. https://doi.org/10.1080/02571862.2006.10634746

[18]. Griepentrog HW, Noerremark M, Soriano JF (2006) Close-to-crop thermal weed control using a CO2 laser. In: Proceedings: CIGR World Congress, Agricultural Engineering for a Better World, Bonn, Germany, 3rd–7th September

[19]. Hanson B, Peters D, Orloff S (2000) Effectiveness of tensiometers and electrical resistance sensors varies with soil conditions. Calif Agric 54:47–50. https://doi.org/10.3733/ca.v054n03p47

[20]. Heisel T, Schou J, Christensen S, Andreasen C (2001) Cutting weeds with a CO2 laser. Weed Res 41:19–29. https://doi.org/10.1046/j.1365-3180.2001.00212.x

[21]. Jani K, Chaudhuri M, Patel H, Shah M (2020) Machine learning in films: an approach towards automation in film censoring. J Data Inf Manag 2:55–64. https://doi.org/10.1007/s42488-019-00016-9
[22]. Jesus J, Panagopoulos T, Neves A (2008) Fuzzy logic and geographic information systems for pest control in olive culture. In: 4th IASME/WSEAS International Conference on Energy, Environment, Ecosystems & Sustainable Development, Algarve, Portugal, June, pp 11–13

[23]. Ji B, Sun Y, Yang S, Wan J (2007) Artificial neural networks for rice yield prediction in mountainous regions. J Agric Sci 145:249–261

[24]. Karimi Y, Prasher SO, Patel RM, Kim SH (2006) Application of support vector machine technology for weed and nitrogen stress detection in corn. Comput Electr Agric 51(1–2):99–109. https://doi.org/10.1016/j.compag.2005.12.001

[25]. Kolhe S, Kamal R, Saini HS, Gupta GK (2011) An intelligent multimedia interface for fuzzy-logic based inference in crops. Expert Syst Appl 38:14592–14601
[26]. Lal H, Jones JW, Peart RM, Shoup WD (1992) FARMSYS—a whole-farm machinery management decision support system. Agric Syst 38:257–273

[27]. Lasanta T, Vicente-Serrano SM (2012) Complex land cover change processes in semiarid Mediterranean regions: an approach using Landsat images in northeast Spain. Remote Sens Environ 124:1–14. https://doi.org/10.1016/j.rse.2012.04.023

[28]. Levine ER, Kimes DS, Sigillito VG (1996) Classifying soil structure using neural networks. Ecol Model 92(1):101–108. https://doi.org/10.1016/0304-3800(95)00199-9
[29]. López EM, García M, Schuhmacher M, Domingo JL (2008) A fuzzy expert system for soil characterization. Environ Int 34:950–958

[30]. López-Granados F (2011) Weed detection for site-specific weed management: mapping and real-time approaches. Weed Res 51:1–11. https://doi.org/10.1111/j.1365-3180.2010.00829.x

[31]. Milberg P, Hallgren E (2004) Yield loss due to weeds in cereals and its large-scale variability in Sweden. F Crop Res 86:199–209

[32]. Mogili UMR, Deepak B (2018) Review on application of drone systems in precision agriculture. Proc Comput Sci 133:502–509. https://doi.org/10.1016/j.procs.2018.07.063

[33]. Möller J (2010) Computer vision—a versatile technology in automation of agricultural machinery. J Agric Eng 47:28–36

[34]. Montas H, Madramootoo CA (1992) A decision support system for soil conservation planning. Comput Electr Agric 7(3):187–202. https://doi.org/10.1016/S0168-1699(05)80019-5
[35]. Moran MS, Inoue Y, Barnes EM (1997) Opportunities and limitations for image-based remote sensing in precision crop management. Remote Sens Environ 61:319–346
[36]. Nakai S, Yamada Y (2014) Development of a weed suppression robot for rice cultivation: weed suppression and posture control. Int J Electr Comput Electron Commun Eng 8:1736–1740

[37]. Neil Harker K (2001) Survey of yield losses due to weeds in central Alberta. Can J Plant Sci 81:339–342
[38]. Pérez-Ortiz M, Gutiérrez PA, Peña JM, et al (2016) Machine learning paradigms for weed mapping via unmanned aerial vehicles. In: 2016 IEEE symposium series on computational intelligence (SSCI). IEEE, pp 1–8

[39]. Peruzzi A, Ginanni M, Fontanelli M et al (2007) Innovative strategies for on-farm weed management in organic carrot. Renew Agric Food Syst 22:246–259
[40]. Plant RE, Horrocks RD, Grimes DW, Zelinski LJ (1992) CALEX/Cotton: an integrated expert system application for irrigation scheduling. Trans ASAE 35(6):1833–1838. https://doi.org/10.13031/2013.28803
[41]. Qualls RJ, Scott JM, DeOreo WB (2001) Soil moisture sensors for urban landscape irrigation: effectiveness and reliability 1. JAWRA J Am Water Resour Assoc 37:547–559. https://doi.org/10.1111/j.1752-1688.2001.tb05492.x

[42]. Rajpal A, Jain S, Khare N, Shukla AK (2011) Microcontroller-based automatic irrigation system with moisture sensors. In: Proceedings of the International Conference on Science and Engineering. pp 94–96

[43]. Rao AN, Wani SP, Ladha JK (2014) Weed management research in India-an analysis of past and outlook for future

[44]. Shah G, Shah A, Shah M (2019) Panacea of challenges in real-world application of big data analytics in healthcare sector. J Data Inf Manag 1:107–116. https://doi.org/10.1007/s42488-019-00010-1
[45]. Shamshiri RR, Weltzien C, Hameed IA, J Yule I, E Grift T, Balasundram SK, Pitonakova L, Ahmad D, Chowdhary G (2018) Research and development in agricultural robotics: a perspective of digital farming. Int J Agric Biol Eng 11(4):1–11. https://doi.org/10.25165/j.ijabe.20181104.4278
[46]. Shekhar Y, Dagur E, Mishra S, Sankaranarayanan S (2017) Intelligent IoT based automated irrigation system. Int J Appl Eng Res 12:7306–7320

[47]. Song H, He Y (2005) Crop nutrition diagnosis expert system based on artificial neural networks. In: Third international conference on information technology and applications (ICITA’05), 2005 Jul 4, vol 1, pp 357–362. IEEE. https://doi.org/10.1109/ICITA.2005.108
[48]. Tothill IE (2001) Biosensors developments and potential applications in the agricultural diagnosis sector. Comput Electron Agric 30:205–218

[49]. Tu M, Hurd C, Randall JM (2001) Weed control methods handbook: tools & techniques for use in natural area.
[50]. van Mourik S, van der Tol R, Linker R et al (2021) Introductory overview: systems and control methods for operational management support in agricultural production systems. Environ Model Softw 139:105031
[51]. Wang Y, Huang L, Wu J, Xu H (2007) Wireless sensor networks for intensive irrigated agriculture. In: 2007 4th IEEE Consumer Communications and Networking Conference. IEEE, pp 197–201

[52]. World Bank (2022) World Bank Data: Annual Freshwater Withdrawals, Agriculture (% of Total Freshwater Withdrawal). https://data.worldbank.org/indicator/ER.H2O.FWAG.ZS?end=2016&start=2011&view=chart. Accessed 01 Oct 2022
[53]. Yang CC, Prasher SO, Landry J, Ramaswamy HS (2012) Development of neural networks for weed recognition in corn fields. Trans ASAE 45(3). https://doi.org/10.13031/2013.8854