Introduction
In the US, psyllids are commonly known and designated as ‘citrus greening infection’. Farmers who specialize in citrus production in Florida expect more than $7 billion in income in return for their investments (Ampatzidis et al., 2019). Scientists have had an interested to identify trees with the condition and eliminate them from fields. There have been several trees infected with Huanglongbing (HLB) found in California, with issues being how to manage or identify the condition with ease (Byrne et al., 2017). It is common for farmers to take immediate action after identifying a tree with the illness to ensure they reduce the probability of the infection from spreading to the other healthy plants in the surrounding (Ampatzidis et al., 2019). Artificial Intelligence (AI) has offered innovative solutions to capture and record information that facilitates and improves the research and development processes. For instance, SeeTree utilizes robots, sensors, and people to catch pictures and record information that AI can parse for data. The outcome is an itemized investigation of every individual tree on a plantation with a harvest yield examination and wellbeing profile.
Sophisticated technology has developed across the world allowing industries to adopt cost-effective production methods that increase the profits realized at the end of each operating period. Industries globally have invested in research and development to come up with creative and innovative ways in which they can simplify the work done (Tang et al., 2021). Agriculturists have also found the methods to ensure crop production is at a high level; management of plant diseases is easy and resilient seeds that can survive different weather conditions in various parts of the world. Citrus farming is one of the most profitable activities globally with farmers producing raw materials to manufacture different products. Demand for citrus has increased over the years which motivates farmers to increase their yield every harvesting period. However, the dangerous psyllids have been a threat that discourages farmers from investing in the fruit due to the impact the disease has on the plant both in the short-term and in the long-term.
Psyllids are highly infectious since it has a high probability of being infected with greening, which then transmits and spreads the disease to citrus plants. According to Ampatzidis et al. (2019), greening has spread to more than 40 nations across the globe, affirming that other countries are at risk due to the trade activities and open boundaries. For instance, in Florida County, the production rate decreased by more than 70% between 2000 and 2017 (Ampatzidis et al., 2019). Farmers were mainly discouraged and affected by the tremendous losses resulting from greening after psyllids penetrated the region in 2005.
Background
Asian-based citrus psyllids are some of the smallest trees that produce fruit, but they affect global production due to their risk of getting the greening disease. Psyllids have been detected using the ‘tap sample method’ when they strike branches and affect the entire plant as well as its probability to increase in size. Local farmers from Florida reported cases of psyllids in their farms after electronic methods were used to detect the presence of the condition (Byrne et al., 2017). Automated systems were easier, faster, and more effective in collecting and analyzing the data from the machine vision. AI has been incorporated into the equipment used to capture trees’ images and insects that attack the citrus groves (Partel et al., 2019). The justification for using AI in the management of citrus diseases is that it has the comparative advantage of differentiating psyllids and other pests that attack the citrus groves and affect their growth rate.
The AI-enabled machine comprises a tapping mechanism that highlights some branches that have been pre-selected with a grid of cameras. After pictures have been taken and developed, the AI algorithm has the power and capacity to analyze images, and potential defects, and quantify the adult psyllids (Byrne et al., 2017). The justification for using AI-based systems is that they have a high accuracy rate with psyllids being detected and identified at a 90% precision level (Ampatzidis et al., 2019). Farmers’ use of digital systems in enhancing crop production which allows them to have high yields in the long term.
Each citrus grove that has a camera sends specific information about the psyllids attacking such a plant, with the data collected enhancing the development of maps. This means researchers and farmers are more informed and can apply or spray the right amount of pesticides on plants that have pests (Tang et al., 2021). Protection of the environment through agrochemical use and other associated expenses for the farmer is reduced by a large margin since only the right quantity of pesticide is applied. Harvest management and yield mapping systems are embraced in the farms which ensure that all plants that would generate incomes for the farmers have been incorporated. Sustainable methods that would support citrus farming would enhance the use of modernized techniques and technologies to identify the stress status of plants as well as crop health (Deng et al., 2020). Detecting early diseases and pests affects the yield produced at the end of each period. AI makes it easy to distinguish other deficiencies in the citrus fruits, recognizing the fact that other conditions may have similar symptoms, and if left untreated, may affect the production levels.
Details and Description
AI can play an important role in detecting psyllids in citrus framing in the management of citrus greening. AI is suitable for the management and detection of diseases since it is fast and easy as it uses technology to collect and analyze all relevant data. Ampatzidis et al. (2019) claimed that knowledge about the psyllid populace is crucial for all citrus growers as it allows them to make informed decisions on the best AI system to utilize. The conventional method of detecting psyllids on a branch, the tap sample method, is tedious and labor-intensive compared to the robotic system that incorporates machine vision as well as artificial intelligence. Automating the scouting process would simplify the work done by machines and it would be possible to detect other insects using the system (Deng et al., 2020). Specialized AI-based software is inserted into the machine with the GPS device which is used to easily locate each tree on a farm. Later, the software generates a map informing the farmer of all psyllid infections in their farms. The developed psyllid data allows the farmers to make the right decision.
AI is best suited for the detection and management of psyllid due to its ability to attack all different types of citrus plants in the Rutaceae family. The pest attacks the new budded citrus leaf with its toxin saliva which results in the leaf turning black. The psyllid causes more damage to a farm since it results in the Huanglongbing (HLB) disease which leads to the shoots turning yellow. Fruits become asymmetrical in shape, get bitter juice, and seeds get aborted in the process (Nakabachi & Okamura, 2019). There is no cure for the psyllids disease and within 5 or 8 years, a citrus tree dies and is no longer beneficial to the farmer. Early detection or identification of the psyllid pests is crucial to the survival rate of the rest of the farm. Ampatzidis et al. (2019) claimed that the Asian citrus psyllid first arrived from Mexico in 2008 and was detected in California in the Southern parts, affirming that immediate response should be administered whenever it is first identified. Illegal imports from Mexico may have brought the pests in the US to different states.
AI is best suited for the detection and management of psyllids since it allows farmers to reduce the transmission of pests from one part to others. Pesticides have a high ability to reduce the number of psyllids on plants, but since it is impossible to kill all adult psyllids that spread the bacteria, AI plays a great role in keeping the psyllid numbers the minimum on each orchid farm (Rehberg et al., 2020). Identification of the adult psyllids through AI systems is viable through the constant visual surveys taken through the digitalized technologies. Visual monitoring systems make it possible for farmers to eliminate the eggs and young nymphs which means their probability of becoming adults and causing more damage is low (Nakabachi & Okamura, 2019). Pesticides used in citrus farms vary since they are unable to kill the psyllids in all their life-cycle stages. It is common for some pesticides to be effective in one life cycle compared to another.
Methodology
The study employed a secondary research method and design to increase the accuracy and validity of the results presented at the end. A qualitative method was applied in the research with results from other scholars being examined to identify what has already been addressed in the issue of psyllids in citrus farming. Research is a process of collecting information that widens one’s understanding of a particular issue. This methodology will emphasize the use of the secondary research approach, which comprises the collection and analysis of already collected and analyzed data from previous research on the subject (Creswell, 2015). This method is the best option for this exploration since the issue of interest is how AI is relevant in the management of psyllids in citrus plants.
Constant studies are being conducted by researchers as they examine alternative methods of managing psyllids since there is no current cure for the condition. Even though it is time-consuming, this method is accurate and precise. The selection of this design focuses on the particular amount and type of data that is relevant to the objective of the study. Furthermore, this design provides significant information that can help in improving the status of this study and rectifying any issues regarding the subject. Secondary research provides efficient data from numerous studies carried out by different authors. It offers an easy platform for the author to find all the information needed since it is readily available and the researcher has enough time to summarize and edit the findings. Although the primary data collection method is the best strategy for finding all the information required, in this context, the secondary research method is the most applicable when the researcher uses qualitative methods to gather facts from different sources (Esser & Vliegenthart, 2017). The design used in this examination does not affect the analysis or data collection of its sources, unlike other exploration methods. The analysis collected in the research using the data gathered with the qualitative approach provides an efficient platform for editing and solving the issues analyzed.
The secondary research method finds data in journals, newspapers, books, and websites. The data used should be trustworthy in that the sources will have a publication year and date, the author’s name, the particular published place, and the references (Esser & Vliegenthart, 2017). A high percentage of this review is from journals that will all have met academic standards so that they can be used by students. Secondary research can still bring out the qualitative aspects of the study. The qualitative approach mainly reviews documents from secondary research. The use of a qualitative method in this study provides satisfying outcomes in identifying the relevance of AI in farming.
Working Analysis of AI in Citrus
AI technology has penetrated the farming industry with producers embracing precision tools and techniques that enable the collection of high data volumes for effective and efficient decision-making processes. In a contrast, conventional methods of collecting data related to crop production and yield or management of vast commercial farms were almost impossible since they required the physical involvement of the farmers (Barbedo & Castro, 2020; Partel et al., 2019). Digital methods are simpler and faster, and their high accuracy levels ensure that all areas of the fields have been captured. AI in citrus farming is crucial as it allows automated aerial surveys with digitalized drones to view the groves (Ampatzidis et al., 2019). AI as a machine has the capability of using computer algorithms with little or no human intervention, with farmers only being required to collect the processed data.
Sophisticated models have been designed and trained to capture psyllids, with eggs that have been freshly laid by the females being detected immediately. This justifies why it has been easy to understand the different life-cycle processes and patterns the psyllids undergo, and it has been possible to develop pesticides best suited for every stage (Nakabachi & Okamura, 2019). With more knowledge about psyllids being available, there is a high probability that better management methods will be developed in the future. The convenience created by AI research cannot be ignored due to the simplified real-time information it provides to the farmers. Photographs taken by the attached cameras provide clear pictures that enable researchers and farmers to identify objects and relevant situations that affect the growth of citrus fruits including other pests, weeds, or diseases (Ampatzidis et al., 2019; Lu et al., 2019). AI has also facilitated the use of alternative methods of nurturing and growing the citrus groves, especially in protected screen houses that have a low probability of being exposed to the Asian citrus psyllid (ASP). Factors that contribute to the exposure of psyllids in normal orchard farms are prevented.
Advantages and Disadvantages
AI has played a pivotal role in the management of psyllids in citrus fruits as it has supported early detection and proactive measures taken to curb the spread of the condition. Identification of the problem at the initial stages enables farmers to take immediate measures that ensure all their citrus groves have not been infected (Lu et al., 2019). Measures such as cutting down the infected groves to limit the spread are productive. Farmers are also informed of alternative ways which help them protect their farms. New information released to the farmers allows them to save money and invest in the right type of citrus seed that is more resilient. AI has replaced the ‘tap sample method’ that was time-consuming and did not provide the farmers with the correct data related to the infection rate in their farms (Nakabachi & Okamura, 2019). The AI systems use an automated system that updates itself automatically, thereby enhancing the decision-making process.
Localized crop management has been made possible through the application of AI automated systems. Tables, maps, and graphs generated by the captured images from the attached cameras summarize the developments and changes that have been taking place on the farms (Partel et al., 2019). Such data is relevant for farmers as it informs them if the levels have increased or decreased, and the measures they should undertake to curb the problem. Farmers precisely understand the condition of their farms with proactive measures to prevent psyllids from affecting their farms since such have negative effects on the health and stability of the plants.
One of the limitations is that not all farmers can easily set up an AI system on their farms as the installation process might be expensive. AI systems are only applicable in commercial firms that generate high returns and can easily sustain such an investment. Hence, farms in some rural settings in the US might continue supporting the breeding of psyllids indirectly, which means it might be impossible to eliminate them in the country (Deng et al., 2020; Rehberg et al., 2020). Government support and intervention may allow small farms to control or eliminate the problem of psyllids in their farms.
Image processing using machine learning algorithms might be complicated and extensive for farmers with little or no knowledge, affirming that AI management of psyllids maybe not be effective in all parts of the country. This means researchers and specialists should be present on farms to handle the AI machines and interpret the data collected for the farmers (Nouri et al., 2016; Tang et al., 2021). This creates a high level of inconvenience and opposition from farmers as they consider the adoption of AI automated systems to be irrelevant and costly to maintain and manage. There is a high probability that captured images may need more processing to provide more information.
Future Research
Weaknesses and limitations identified when conducting the research act as the foundation for future research as scholars could review the issues faced by previous researchers and use them as the basis for their next processes. The research used in the study failed to identify the most appropriate methods farmers in different parts of the world have used as they have been biased in the US. Most available research addresses the history of psyllids in Florida and California states, affirming that its genesis was Mexico. Recognizing the genesis of the problem is important, but the management of the issue that facilitated the movement of the pests from Mexico to the US is equally crucial as it will prevent other crops from getting infected by foreign diseases.
Little or no consideration has been given to the management strategies Mexican farmers utilize that would also be implemented in other parts of the world using a more personalized approach based on the needs of the country. Further, there has been limited attention to the role the government plays in ensuring psyllids have been eliminated or controlled in the citrus farming industry (Byrne et al., 2017). Governments have a responsibility of coming up with independent research institutes for their local farmers to ensure resilient and higher-yield seeds have been manufactured that will withstand diseases and harsh weather conditions. Working closely with the government would enable farmers to have more confidence in the management of psyllids.
Conclusion
Management of psyllids using AI methods has been effective, with timely and informed decisions being made to help prevent the spread of the pests on farms or across the world. There is no cure for psyllids, but ongoing research and development centers have a high probability of releasing new information related to the management of the condition. Robotic systems have been developed and designed in a manner that they are self-sufficient and can independently move across the farm while collecting and sending information with little or no human assistance. Cameras attached to the AI machines capture all information, and researchers are in a position to easily identify all types of pests. AI machines have a GPS, which makes it easy for the farmers to locate them in the farms, while the camera with different photo resolutions takes images from various angles. Government intervention and assistance would contribute to the management of psyllids through the establishment of research and development centers.
References
Ampatzidis, Y., Partel, V., Meyering, B., & Albrecht, U. (2019). Citrus rootstock evaluation utilizing UAV-based remote sensing and artificial intelligence.Computers and Electronics in Agriculture, 164, 104900. Web.
Barbedo, J. G. A., & Castro, G. B. (2020). A study on CNN-Based detection of psyllids in sticky traps using multiple image data sources.AI, 1(2), 198-208. Web.
Byrne, F. J., Daugherty, M. P., Grafton Cardwell, E. E., Bethke, J. A., & Morse, J. G. (2017). Evaluation of systemic neonicotinoid insecticides for the management of the Asian citrus psyllid Diaphorina citri on containerized citrus.Pest Management Science, 73(3), 506-514. Web.
Deng, X., Zhu, Z., Yang, J., Zheng, Z., Huang, Z., Yin, X., & Lan, Y. (2020). Detection of citrus huanglongbing based on multi-input neural network model of UAV hyperspectral remote sensing.Remote Sensing, 12(17), 2678. Web.
Esser, F., & Vliegenthart, R. (2017). Comparative research methods.The international encyclopedia of communication research methods, 1-22. Web.
Lu, Z. J., Huang, Y. L., Yu, H. Z., Li, N. Y., Xie, Y. X., Zhang, Q., &Zeng, X. D., Hu, H., Huang, A. J., Yi, L., & Su, H. N. (2019). Silencing of the chitin synthase gene is lethal to the Asian citrus psyllid, Diaphorina citri.International Journal of Molecular Sciences, 20(15), 3734. Web.
Nakabachi, A., & Okamura, K. (2019). Diaphorin, a polyketide produced by a bacterial symbiont of the Asian citrus psyllid, kills various human cancer cells.PloS One, 14(6), e0218190. Web.
Nouri, S., Salem, N., Nigg, J. C., & Falk, B. W. (2016). Diverse array of new viral sequences identified in worldwide populations of the Asian citrus psyllid (Diaphorina citri) using viral metagenomics.Journal of Virology, 90(5), 2434-2445. Web.
Partel, V., Nunes, L., Stansly, P., & Ampatzidis, Y. (2019). Automated vision-based system for monitoring Asian citrus psyllid in orchards utilizing artificial intelligence. Computers and Electronics in Agriculture, 162, 328-336. Web.
Rehberg, R. A., Trivedi, P., Bahureksa, W., Sharp, J. L., Stokes, S. C., Menger, R., & Borch, T. (2020). Quantification of insecticide spatial distribution within individual citrus trees and efficacy through Asian citrus psyllid reductions under different application methods.Pest Management Science. Web.
Tang, T., Zhao, M., Wang, P., Huang, S., & Fu, W. (2021). Control efficacy and joint toxicity of thiamethoxam mixed with spirotetramat against the Asian citrus psyllid, Diaphorina citri Kuwayama.Pest Management Science, 77(1), 168-176. Web.