italianoenglishfrançaisdeutschespañolportuguês
Language
Search
  • » Technical Articles
  • » How artificial intelligence (AI) is helping winegrowers to deal with adversity from climate change

How artificial intelligence (AI) is helping winegrowers to deal with adversity from climate change

Sigfredo Fuentes et al., The University of Melbourne - Australia

Sigfredo Fuentes1*, Eden Tongson1 and Claudia Gonzalez Viejo1

1Digital Agriculture, Food and Wine Research Group. School of Agriculture and Food. Faculty of Veterinary and Agricultural Sciences. The University of Melbourne. Royal Parade. 3010. Victoria. Australia.


*Corresponding author:  sfuentes@unimelb.edu.au

 

Article extracted from the presentation held during Enoforum Web Conference (23-25 February 2021)

______________________________________________________________________________________________________

Abstract

Climate change has posed major risks for viticulture and winemaking around the world, related to increased ambient temperatures, the variability of rain events, higher occurrence and intensity of climatic anomalies, such as frosts and bushfires. These changes have directly impacted grapevine phenology by compressing stages and pushing forward in time harvest to hottest months, producing a dual warming effect. Bushfires also directly impact berry smoke contamination, which can be passed to the wine in the winemaking process producing smoke taint. Due to these events' complexities and their effects on viticulture and winemaking, a smarter approach is required to obtain relevant information and process it efficiently for more appropriate decision-making by different practitioners. In the last 10 years, artificial intelligence has offered various applications to be included in viticultural and winemaking operations, which has rendered important advances and information to deal with climate change adversities.


Introduction

Precision viticulture (PV) has been around for more than two decades, which deals with sensor technology and instrumentation to aid different viticultural operations. However, considering the scale of applications, the main broad implementation of PV has been in the automation of machinery aided by geo-positioning data. Digital Agriculture and Viticulture (DA and DV) have gained more recognition and have been adopted by different research institutions and universities worldwide as an effective and easier system to be implemented to viticultural and winemaking operations. The main difference between PV and DV is that the former deals with the technology and hardware used, such as sensors and sensor networks, sensors attached to machinery for automation of viticultural management remote sensing using different platforms, such as satellite airborne and unmanned aerial vehicles (UAVs) offering different temporal and spatial resolutions. In the DV case, it deals more with what is done with the data obtained from different sensors and platforms and how these data are analyzed. Data analysis in DV can be from signal analysis to computer vision algorithms and different modelling strategies [1]. For automation purposes, the latest modelling strategies have been performed in the context of Artificial Intelligence (AI), from which machine learning is one of its sub-disciplines. AI can interact with other digital disciplines, such as computer vision, robotics, biometrics, integrated sensor, and sensor networks, to obtain data, learn from them through different machine learning algorithms and target different parameters of interest for management purposes for viticultural and winemaking operations.

This paper explores the latest DV applications and AI combined in viticulture and winemaking to help winegrowers deal with the complexities posed by climate change conditions. It is important to note that many of the latest research and applications using PV technologies have not used machine learning or AI for data analysis. In that case, those studies were considered outside the scope of this paper.


Biological sensors and digital viticulture

One of the novel technologies that have been implemented in DV is the introduction of biological sensors in combination with digital sensors. In the case of DV, dogs have been trained to detect different pests and diseases. This application of dogs is not new since they have been trained to detect illicit drugs, money, and food at border control points such as airports. However, novel applications using trained dogs have been recently implemented to detect diseases in plants and humans, such as COVID-19, with high precision that can reach over 95% [2, 3]. Dogs have 100 times more sensitive noses than humans and can be trained to detect compounds that can be present in parts per trillion. In DV, dogs have been trained to detect one of the most important insects in the industry, Phylloxera. It has been shown that dogs can detect the insect even underground (unpublished data).

The digital approach adopted with these biological sensors is in the form of computer applications (apps) in smartphones located on dog’s backpacks, which can record the accelerometer and geo-position data from the mobile devices. This system has been used to train an AI algorithm to detect when the dog is running or detecting the targeted stimuli. The AI algorithm needs to be calibrated by different dogs trained to sit, crouch, or scratch the place where the specific stimuli are detected. The first app developed for these purposes is Inspector Paw © [4], which has been tested to create different AI models for dogs by the Digital Agriculture, Food and Wine Research group (University of Melbourne).


Remote sensing and AI

In the context of the soil-plant-atmosphere continuum, applications of DV and AI are less in number for soil applications compared to plant-based and mainly based on soil moisture predictions [5], soil organic carbon [6], prediction of soil properties [7]. For applications based on the grapevines, the number of applications is significantly higher, mainly to assess vine water status for irrigation purposes using multispectral [8], hyperspectral [9] and proximal [10] remote sensing. Prediction of pests and diseases using DV and AI [11] present more complex machine learning modelling [12], including deep learning [11, 13, 14] and remote sensing [15]. Other novel applications using integrated sensor technologies, such as electronic noses (e-noses), have been used in viticulture to detect diseases [16]. Further research, including DV and AI, have focused on fertilizer deficiency detection and smart application [17-19]

Classification of varieties through a digital ampelography approach could offer the differentiation and recognition of different cultivars and strategies to detect small differences from established vineyards that can be related to changes due to biotic and abiotic stresses [20, 21]. Similar approaches have been used to detect invasive weeds implemented using low-cost smart technology [22], computer vision and deep learning, and smart spray [23]. In the case of canopy management, a dedicated free App: VitiCanopy(The University of Adelaide, Australia) to acquire information from canopies using computer vision was developed in 2014 and has been used by many researchers and viticultural managers worldwide [24]. Parameters from VitiCanopy have been used to link them to grape quality trait parameters [25] and the same using machine learning for grapevines (unpublished) in a similar manner of published data for cocoa trees [26]. Finally, big data, based either on historical records of phenology and meteorological information, have also been implemented AI for cultivar identification [27] and to predict harvest time [28]. Finally, yield prediction has gained a special interest in DV implementing AI-based on computer vision and deep learning [29], based on berries and clusters [30, 31] and for phenotyping purposes [32-34].


Winemaking and consumer acceptability using AI

One of the major threats for grape production and winemaking is the increased number, severity, and window of opportunity of bushfires around the world for grape-growing regions due to climate change. Smoke affecting vineyards can contaminate berries passing these smoke-related compounds to the wine known as smoke taint [35]. Different digital and non-destructive sensors coupled with AI, such as infrared thermography for canopies, have been used to detect smoke contaminated vines and near-infrared spectroscopy to detect smoke-related compounds in grapes and final wine [36-38]. Low-cost e-noses have also been developed to detect smoke taint in berries and wine [39].

New sensory analysis technologies have been developed to assess more objective responses from panellists towards different food and beverage products, including wine. These new technologies are based on biometrics and physiological responses from panellists assessed from video analysis and remote sensing techniques while tasting different products [40, 41]. AI application based on biometrics, has been applied for different beverages [42, 43], combined with robotic beverage pourers and integrated e-noses [44-48].

Wine quality assessment using AI has also gathered the attention of researchers [49, 50]. Supervised machine learning has been applied to assessing different wine features [51-54]. Big data has also been applied along with AI for early prediction of aroma profiles of final wines [55] and the use of non-destructive NIR readings to predict the effect of the berry mesocarp cell death on grape quality traits and aroma profile of final wines [56].


Data access, ownership and security access using AI

One of the main problems in DV and any AI implementation is the insecurity from the winegrower’s perspective regarding data access, data ownership and security. For them, it is not always clear who owns the data acquired from their vineyards and wineries. There is also a great uncertainty towards whether third parties can use the data and corresponding analysis to benefit competitors. The latter, especially if providers of DV and AI solutions, are private companies working with cloud computing. One relatively straightforward solution to this problem would be treating the data generated from specific vineyards or wineries as currency and secured using an electronic ledger format for traceability, such as blockchain [57-62]. This will ensure winegrowers and winemakers that access to the data is restricted, and there will be indelible records of who access the data, how many times and when.


Conclusion

Even though the latest DV and AI advances in the last five years have been promising, there is still no integratory vision in the newest research. This could be mainly related to specific skills from different research groups specialized either in viticultural or winemaking and sensory analysis processes. The Digital Agriculture, Food and Wine research group has proposed an integrative approach from the vineyard to the palate, which essentially implements novel AI tools developed though DV from the vineyard, harvest, grape processing, winemaking, and consumer sensory perception. Information of this production chain can then be fed back to the vineyard through AI models to target specific quality traits or wine styles preferred by consumers and winemakers. This novel approach will consider climate change constraints and the complexity of the variability related to weather, seasonality, and consumer preference changes. This integrative approach could revolutionize the winemaking industry and secure competitiveness in international markets by small, medium, and big companies.


 

References

1. Seng, K.P., et al., Computer vision and machine learning for viticulture technology. IEEE Access, 2018. 6: p. 67494-67510.

2. Jendrny, P., et al., Scent dog identification of samples from COVID-19 patients–a pilot study. BMC infectious diseases, 2020. 20(1): p. 1-7.

3. Jones, R.T., et al., Could bio-detection dogs be used to limit the spread of COVID-19 by travellers? Journal of travel medicine, 2020. 27(8): p. taaa131.

4. Fuentes, S. and E. Tongson, Advances and requirements for machine learning and artificial intelligence applications in viticulture. Wine & Viticulture Journal, 2018. 33(3): p. 47-52.

5. Hajjar, C.S., et al. Machine learning methods for soil moisture prediction in vineyards using digital images. in E3S Web of Conferences. 2020. EDP Sciences.

6. Wang, B., et al. Estimating soil organic carbon stocks using machine learning methods in the semi-arid rangelands of New South Wales. in 22nd International Congress on Modelling and Simulation: Hobart, Tasmania, Australia. 2017.

7. Ma, Y., et al., Predicting soil properties in 3D: Should depth be a covariate? Geoderma, 2021. 383: p. 114794.

8. Romero, M., et al., Vineyard water status estimation using multispectral imagery from an UAV platform and machine learning algorithms for irrigation scheduling management. Computers and electronics in agriculture, 2018. 147: p. 109-117.

9. Pôças, I., et al., Hyperspectral-based predictive modelling of grapevine water status in the Portuguese Douro wine region. International journal of applied earth observation and geoinformation, 2017. 58: p. 177-190.

10. Gutiérrez, S., et al., Vineyard water status assessment using on-the-go thermal imaging and machine learning. PLoS One, 2018. 13(2): p. e0192037.

11. Shruthi, U., V. Nagaveni, and B. Raghavendra. A review on machine learning classification techniques for plant disease detection. in 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS). 2019. IEEE.

12. Cruz, A., et al., Detection of grapevine yellows symptoms in Vitis vinifera L. with artificial intelligence. Computers and electronics in agriculture, 2019. 157: p. 63-76.

13. Gutiérrez, S., et al., Deep learning for the differentiation of downy mildew and spider mite in grapevine under field conditions. Computers and Electronics in Agriculture, 2021. 182: p. 105991.

14. Cruz, A.C., A. El-Kereamy, and Y. Ampatzidis. Vision-based grapevine pierce’s disease detection system using artificial intelligence. in 2018 ASABE Annual International Meeting. 2018. American Society of Agricultural and Biological Engineers.

15. Abdulridha, J., et al., Detecting powdery mildew disease in squash at different stages using UAV-based hyperspectral imaging and artificial intelligence. Biosystems Engineering, 2020. 197: p. 135-148.

16. Prabha, K., Disease sniffing robots to apps fixing plant diseases: applications of artificial intelligence in plant pathology—a mini review. Indian Phytopathology, 2020: p. 1-8.

17. Ukaegbu, U., et al. A deep learning algorithm for detection of potassium deficiency in a red grapevine and spraying actuation using a raspberry pi3. in 2020 International Conference on Artificial Intelligence, Big Data, Computing and Data Communication Systems (icABCD). 2020. IEEE.

18. Jha, K., et al., A comprehensive review on automation in agriculture using artificial intelligence. Artificial Intelligence in Agriculture, 2019. 2: p. 1-12.

19. Rahaman, D.M., et al. Grapevine Nutritional Disorder Detection Using Image Processing. in Pacific-Rim Symposium on Image and Video Technology. 2019. Springer.

20. Gutiérrez, S., et al., On-the-go hyperspectral imaging under field conditions and machine learning for the classification of grapevine varieties. Frontiers in plant science, 2018. 9: p. 1102.

21. Fuentes, S., et al., Automated grapevine cultivar classification based on machine learning using leaf morpho-colorimetry, fractal dimension and near-infrared spectroscopy parameters. Computers and electronics in agriculture, 2018. 151: p. 311-318.

22. Partel, V., S.C. Kakarla, and Y. Ampatzidis, Development and evaluation of a low-cost and smart technology for precision weed management utilizing artificial intelligence. Computers and Electronics in Agriculture, 2019. 157: p. 339-350.

23. Partel, V., et al., Smart Sprayer for Precision Weed Control Using Artificial Intelligence: Comparison of Deep Learning Frameworks. 2019.

24. De Bei, R., et al., VitiCanopy: A free computer App to estimate canopy vigor and porosity for grapevine. Sensors, 2016. 16(4): p. 585.

25. De Bei, R., et al., Canopy architecture is linked to grape and wine quality in Australian Shiraz. 2018.

26. Fuentes, S., et al., Spatial Variability of Aroma Profiles of Cocoa Trees Obtained through Computer Vision and Machine Learning Modelling: A Cover Photography and High Spatial Remote Sensing Application. Sensors, 2019. 19(14): p. 3054.

27. Fernandes, A.M., et al., Grapevine variety identification using “Big Data” collected with miniaturized spectrometer combined with support vector machines and convolutional neural networks. Computers and Electronics in Agriculture, 2019. 163: p. 104855.

28. Kaburlasos, V., et al. Toward Big Data Manipulation for Grape Harvest Time Prediction by Intervals’ Numbers Techniques. in 2020 International Joint Conference on Neural Networks (IJCNN). 2020. IEEE.

29. Silver, D.L. and T. Monga. In vino veritas: Estimating vineyard grape yield from images using deep learning. in Canadian Conference on Artificial Intelligence. 2019. Springer.

30. Coviello, L., et al., GBCNet: In-Field Grape Berries Counting for Yield Estimation by Dilated CNNs. Applied Sciences, 2020. 10(14): p. 4870.

31. Aquino, A., et al., A new methodology for estimating the grapevine-berry number per cluster using image analysis. Biosystems engineering, 2017. 156: p. 80-95.

32. Rist, F., et al., High-precision phenotyping of grape bunch architecture using fast 3D sensor and automation. Sensors, 2018. 18(3): p. 763.

33. Mack, J., et al., Constraint-based automated reconstruction of grape bunches from 3D range data for high-throughput phenotyping. Biosystems Engineering, 2020. 197: p. 285-305.

34. Rudolph, R., et al., Efficient identification, localization and quantification of grapevine inflorescences and flowers in unprepared field images using Fully Convolutional Networks. Vitis, 2019. 58(3): p. 95-104.

35. Summerson, V., et al., Review of the Effects of Grapevine Smoke Exposure and Technologies to Assess Smoke Contamination and Taint in Grapes and Wine. Beverages, 2021. 7(1): p. 7.

36. Fuentes, S., et al., Non-Invasive Tools to Detect Smoke Contamination in Grapevine Canopies, Berries and Wine: A Remote Sensing and Machine Learning Modeling Approach. Sensors (Basel, Switzerland), 2019. 19(15): p. 3335.

37. Summerson, V., et al., Detection of smoke-derived compounds from bushfires in Cabernet-Sauvignon grapes, must, and wine using Near-Infrared spectroscopy and machine learning algorithms. 2020.

38. Summerson, V., et al., Classification of smoke contaminated Cabernet Sauvignon berries and leaves based on chemical fingerprinting and machine learning algorithms. Sensors, 2020. 20(18): p. 5099.

39. Fuentes, S., et al., Assessment of Smoke Contamination in Grapevine Berries and Taint in Wines Due to Bushfires Using a Low-Cost E-Nose and an Artificial Intelligence Approach. Sensors, 2020. 20(18): p. 5108.

40. Fuentes, S., et al., Development of a biosensory computer application to assess physiological and emotional responses from sensory panelists. Sensors, 2018. 18(9): p. 2958.

41. Gonzalez Viejo, C., et al., Non-contact heart rate and blood pressure estimations from video analysis and machine learning modelling applied to food sensory responses: A case study for chocolate. Sensors, 2018. 18(6): p. 1802.

42. Gonzalez Viejo, C., et al., Integration of non-invasive biometrics with sensory analysis techniques to assess acceptability of beer by consumers. Physiology & Behavior, 2018.

43. Gonzalez Viejo, C., et al., Emerging Technologies Based on Artificial Intelligence to Assess the Quality and Consumer Preference of Beverages. Beverages, 2019. 5(4): p. 62.

44. Condé, B.C., et al., Development of a robotic and computer vision method to assess foam quality in sparkling wines. Food Control, 2017. 71: p. 383-392.

45. Gonzalez Viejo, C., et al., Development of a Rapid Method to Assess Beer Foamability Based on Relative Protein Content Using RoboBEER and Machine Learning Modeling. Beverages, 2020. 6(2): p. 28.

46. gonzalez Viejo, C., et al., Development of a low-cost e-nose to assess aroma profiles: An artificial intelligence application to assess beer quality. Sensors and Actuators B: Chemical, 2020: p. 127688.

47. Gonzalez Viejo, C., et al., Development of a robotic pourer constructed with ubiquitous materials, open hardware and sensors to assess beer foam quality using computer vision and pattern recognition algorithms: RoboBEER. Food Research International, 2016. 89: p. 504-513.

48. Gonzalez Viejo, C., et al., Development of Artificial Neural Network Models to Assess Beer Acceptability Based on Sensory Properties Using a Robotic Pourer: A Comparative Model Approach to Achieve an Artificial Intelligence System. Beverages, 2019. 5(2): p. 33.

49. Ramazan, Ü., The Role of Artificial Intelligence in Productivity: A Case Study of Wine Quality Prediction. Avrupa Bilim ve Teknoloji Dergisi, (20): p. 280-286.

50. Shaw, B., A.K. Suman, and B. Chakraborty, Wine Quality Analysis Using Machine Learning, in Emerging Technology in Modelling and Graphics. 2020, Springer. p. 239-247.

51. Aich, S., et al. Prediction of Quality for Different Type of Wine based on Different Feature Sets Using Supervised Machine Learning Techniques. in 2019 21st International Conference on Advanced Communication Technology (ICACT). 2019. IEEE.

52. Agrawal, G. and D.-K. Kang, Wine Quality Classification with Multilayer Perceptron. International Journal of Internet, Broadcasting and Communication, 2018. 10(2): p. 25-30.

53. Lee, S., K. Kang, and D.K. Noh, Wine Quality Assessment Using a Decision Tree with the Features Recommended by the Sequential Forward Selection. 한국컴퓨터정보학회논문지, 2017. 22(2): p. 81-87.

54. Leonardi, G. and L. Portinale. Applying Machine Learning to High-Quality Wine Identification. in Conference of the Italian Association for Artificial Intelligence. 2017. Springer.

55. Fuentes, S., et al., Modeling pinot noir aroma profiles based on weather and water management information using machine learning algorithms: A vertical vintage analysis using artificial intelligence. Foods, 2020. 9(1): p. 33.

56. Fuentes, S., et al., A Digital Approach to Evaluate the Effect of Berry Cell Death on Pinot Noir Wines’ Quality Traits and Sensory Profiles Using Non-Destructive Near-Infrared Spectroscopy. Beverages, 2020. 6(2): p. 39.

57. Bermeo-Almeida, O., et al. Blockchain in agriculture: A systematic literature review. in International Conference on Technologies and Innovation. 2018. Springer.

58. Ge, L., et al., Blockchain for agriculture and food: Findings from the pilot study. 2017: Wageningen Economic Research.

59. Lin, Y.-P., et al., Blockchain: The evolutionary next step for ICT e-agriculture. Environments, 2017. 4(3): p. 50.

60. Yadav, V.S. and A. Singh. A systematic literature review of blockchain technology in agriculture. in Proceedings of the International Conference on Industrial Engineering and Operations Management. 2019.

61. Xiong, H., et al., Blockchain technology for agriculture: applications and rationale. frontiers in Blockchain, 2020. 3: p. 7.

62. Kamble, S.S., A. Gunasekaran, and R. Sharma, Modeling the blockchain enabled traceability in agriculture supply chain. International Journal of Information Management, 2020. 52: p. 101967.

 

Published on 03/29/2022
Pictures
Related sheets
© All Right Reserved
ISSN 1826-1590 VAT: IT01286830334
powered by Infonet Srl Piacenza
- A +
ExecTime : 1,984375