Conference PaperPDF Available

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

Authors:

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.
S. FUENTES ET AL.,HOW ARTIFICIAL INTELLIGENCE (AI) IS HELPING WINEGROWERS, PAGE 1
How artificial intelligence (AI) is helping winegrowers to deal with adversity from climate change
Sigfredo Fuentes1*, Eden Tongson1and 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)
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.
WWW.INFOWINE.COM, INTERNET JOURNAL OF VITICULTURE AND ENOLOGY, 2022, N. 3/4
S. FUENTES ET AL.,HOW ARTIFICIAL INTELLIGENCE (AI) IS HELPING WINEGROWERS, PAGE 2
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
WWW.INFOWINE.COM, INTERNET JOURNAL OF VITICULTURE AND ENOLOGY, 2022, N. 3/4
S. FUENTES ET AL.,HOW ARTIFICIAL INTELLIGENCE (AI) IS HELPING WINEGROWERS, PAGE 3
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.
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
WWW.INFOWINE.COM, INTERNET JOURNAL OF VITICULTURE AND ENOLOGY, 2022, N. 3/4
S. FUENTES ET AL.,HOW ARTIFICIAL INTELLIGENCE (AI) IS HELPING WINEGROWERS, PAGE 4
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.
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
WWW.INFOWINE.COM, INTERNET JOURNAL OF VITICULTURE AND ENOLOGY, 2022, N. 3/4
S. FUENTES ET AL.,HOW ARTIFICIAL INTELLIGENCE (AI) IS HELPING WINEGROWERS, PAGE 5
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.
WWW.INFOWINE.COM, INTERNET JOURNAL OF VITICULTURE AND ENOLOGY, 2022, N. 3/4
S. FUENTES ET AL.,HOW ARTIFICIAL INTELLIGENCE (AI) IS HELPING WINEGROWERS, PAGE 6
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
WWW.INFOWINE.COM, INTERNET JOURNAL OF VITICULTURE AND ENOLOGY, 2022, N. 3/4
S. FUENTES ET AL.,HOW ARTIFICIAL INTELLIGENCE (AI) IS HELPING WINEGROWERS, PAGE 7
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.
WWW.INFOWINE.COM, INTERNET JOURNAL OF VITICULTURE AND ENOLOGY, 2022, N. 3/4
ResearchGate has not been able to resolve any citations for this publication.
Article
Full-text available
Grapevine smoke exposure and the subsequent development of smoke taint in wine has resulted in significant financial losses for grape growers and winemakers throughout the world. Smoke taint is characterized by objectional smoky aromas such as "ashy", "burning rubber", and "smoked meats", resulting in wine that is unpalatable and hence unprofitable. Unfortunately, current climate change models predict a broadening of the window in which bushfires may occur and a rise in bushfire occurrences and severity in major wine growing regions such as Australia, Mediterranean Europe, North and South America, and South Africa. As such, grapevine smoke exposure and smoke taint in wine are increasing problems for growers and winemakers worldwide. Current recommendations for growers concerned their grapevines have been exposed to smoke are to conduct pre-harvest mini-ferments for sensory assessment and send samples to a commercial laboratory to quantify levels of smoke-derived volatiles in the wine. Significant novel research is being conducted using spectroscopic techniques coupled with machine learning modeling to assess grapevine smoke contamination and taint in grapes and wine, offering growers and winemakers additional tools to monitor grapevine smoke exposure and taint rapidly and non-destructively in grapes and wine.
Article
Full-text available
The number and intensity of wildfires are increasing worldwide, thereby also raising the risk of smoke contamination of grapevine berries and the development of smoke taint in wine. This study aimed to develop five artificial neural network (ANN) models from berry, must, and wine samples obtained from grapevines with different levels of smoke exposure (i) Control (C), i.e., neither misting nor smoke exposure; (ii) Control with misting (CM), i.e., in-canopy misting but no smoke exposure; (iii) low-density smoke treatment (LS); (iv) high-density smoke treatment (HS) and (v) a high-density smoke treatment with misting (HSM). Models 1, 2 and 3 were developed using the absorbance values of near-infrared (NIR) berry spectra taken one day after smoke exposure to predict levels of 10 volatile phenols (VP) and 18 glycoconjugates in grapes at either one day after smoke exposure (Model 1: R= 0.98; R2= 0.97; b= 1) or at harvest (Model 2: R= 0.98; R2= 0.97; b= 0.97), as well as six VP and 17 glycoconjugates in the final wine (Model 3: R= 0.98; R2= 0.95; b= 0.99). Models 4 and 5 were developed to predict the levels of six VP and 17 glycoconjugates in wine. Model 4 used must NIR absorbance spectra as inputs (R= 0.99; R2= 0.99; b= 1.00), while Model 5 used wine NIR absorbance spectra (R= 0.99; R2= 0.97; b= 0.97). All five models displayed high accuracies and could be used by grape growers and winemakers to non-destructively assess at near real-time the levels of smoke-related compounds in grapes and/or wine in order to make timely decisions around grape harvest and smoke taint mitigation techniques in the winemaking process.
Article
Full-text available
Wildfires are an increasing problem worldwide, with their number and intensity predicted to rise due to climate change. When fires occur close to vineyards, this can result in grapevine smoke contamination, and subsequently, the development of smoke taint in wine. Currently, there are no in-field detection systems that growers can use to assess whether their grapevines have been contaminated by smoke. This study evaluated the use of near-infrared (NIR) spectroscopy as a chemical fingerprinting tool, coupled with machine learning, to create a rapid, non-destructive in-field detection system for assessing grapevine smoke contamination. Two artificial neural network models were developed using grapevine leaf spectra (Model 1) and grape spectra (Model 2) as inputs, and smoke treatments as targets. Both models displayed high overall accuracies in classifying the spectral readings according to the smoking treatments (Model 1: 98.00%; Model 2: 97.40%). Ultraviolet to visible spectroscopy was also used to assess the physiological performance and senescence of leaves, and the degree of ripening and anthocyanin content of grapes. The results showed that chemical fingerprinting and machine learning might offer a rapid, in-field detection system for grapevine smoke contamination that will enable growers to make timely decisions following a bushfire event, e.g., avoiding harvest of heavily contaminated grapes for winemaking or assisting with a sample collection of grapes for chemical analysis of smoke taint markers.
Article
Full-text available
Bushfires are increasing in number and intensity due to climate change. A newly developed low-cost electronic nose (e-nose) was tested on wines made from grapevines exposed to smoke in field trials. E-nose readings were obtained from wines from five experimental treatments: i) low-density smoke exposure (LS), ii) high-density smoke exposure (HS) and iii) high-density smoke exposure with in-canopy misting (HSM), and two controls: iv) control (C; no smoke treatment) and v) control with in-canopy misting (CM; no smoke treatment). These e-nose readings were used as inputs for machine learning algorithms to obtain a classification model, with treatments as targets and 7 neurons, with 97% accuracy in the classification of 300 samples into treatments as targets (Model 1). Models 2 to 4 used 10 neurons, with 20 glycoconjugates and 10 volatile phenols as targets, measured: in berries one hour after smoke (Model 2; R=0.98; R2=0.95; b=0.97); in berries at harvest (Model 3; R= 0.99; R2 = 0.97; b = 0.96); and in wines (Model 4; R=0.99; R2=0.98; b=0.98). Model 5 was based on the intensity of 12 wine descriptors determined via a consumer sensory test (Model 5; R=0.98; R2=0.96; b=0.97). These models could be used by winemakers to assess near real-time smoke contamination levels and to implement amelioration strategies to minimize smoke taint in wines following bushfires.
Conference Paper
Blockchain has got numerous applications in various fields and one of the promising one is agriculture. The blockchain application in agriculture includes food safety through traceability of provenance, information system, agro-trade, finance, crop certification and insurance etc. Thus this paper aims to review the applications of blockchain in agriculture field from all major databases ranging from Web of Science to Scopus. The study shows that though there exist many blockchain based application in agriculture but only few countries are able to grasp it where China is leader followed by USA, Italy, India and Spain. This paper also reviews the recent trends about blockchain research in agriculture and subsequently provides future research directions. Keywords Agriculture, Blockchain, Future Research Directions, Literature Review, Traceability
Article
Diseases and pests cause serious damage in crop production, reducing yield and fruit quality. Their identification is often time-consuming and requires trained personnel. New sensing technologies and artificial intelligence could be used for automatic identification of disease and pest symptoms on grapevine in precision viticulture. The aim of this work was to apply deep learning modelling and computer vision for the detection and differentiation of downy mildew and spider mite symptoms in grapevine leaves under field conditions. RGB images of grapevine canopy leaves with downy mildew symptoms, with spider mite symptoms and without symptoms were taken under field conditions in a commercial vineyard. The images were prepared using computer vision techniques to increase disease visual features. Finally, deep learning was used to train a model capable of differentiating leaf images of the three classes. An accuracy up to 0.94 (F1-score of 0.94) was obtained by classifying leaves with downy mildew, spider mite and without symptoms at the same time, using a hold-out validation. Additionally, accuracies between 0.89 and 0.91 (F1-scores between 0.89 and 0.91) were obtained in the binary classification of the disease and pest, obtaining the best results in differentiating downy mildew from spider mite symptoms. This high accuracy demonstrates the effectiveness of deep learning and computer vision techniques for the classification of grapevine leaf images taken under field conditions, automatically finding complex features capable of differentiating leaves with spider mite symptoms, with downy mildew symptoms and without any. These results prove the potential of these non-invasive techniques in the detection and differentiation of pests and diseases in commercial crop production.
Article
The recent advancements in artificial intelligence (AI) and machine learning have wide applications in plant pathology with sensors, drones, robots and intelligent monitoring systems. Computer vision based phenotyping of plant stress, diagnostics and severity assessment of plant diseases has gained momentum in horticultural and field crops. Internet of things based on networking sensors for biomarkers of disease like volatile organic compounds are being used for early detection and prediction of plant diseases and host-pathogen interaction studies. Unmanned arial vehicles are employed for phenotyping orchards for precise application of plant protection chemicals. Smartphone based field diagnostics are gaining popularity across the world especially in the remote locations where the laboratory diagnostics of diseases is difficult. AI in plant pathology is still at its infancy. Integration of AI and augmented reality will enhance the accuracy and automation for remote diagnostics of plant diseases and precision plant protection. The “self sufficient, disease free, perfect plant” concept will soon become reality with the help of plant-robot bio-hybrids. This mini review explores the present status of AI technologies in plant pathology and tries to find answers for the questions like what are the common platforms used, which are the diseases where technology is applied, what are the challenges and the future prospects.
Article
Soil is a three-dimensional volume with property variability in all three dimensions. In Digital Soil Mapping (DSM), the variation of soil properties down a profile is usually harmonised by the use of the equal-area spline depth function approach. Soil observations at various depth intervals are harmonised to predetermined depth intervals. To create maps of soil at the defined depth intervals, 2.5D model produces maps of individual depth intervals separately. Those maps can be reconstructed to produce a continuous depth function for each predicted location. More recently, several studies propose that soil property at any depth can be mapped using a model incorporating depth along with spatial covariates as predictor variables, creating a '3D' model. The aim of this study is to evaluate the proposition that soil properties can be predicted at any depth. This study compares the 2.5D model and 3D model in two areas. The first test is on a 1500 km 2 area in Edgeroi, New South Wales (NSW), Australia, mapping soil organic carbon (SOC, %), carbon storage (kg m − 2), pH (H 2 O), clay content (%), and cation exchange capacity (CEC, mg/kg) based on depth-interval observations. The second study area in the Lower Hunter Valley has SOC observations at every 2 cm increment from a 210 km 2 area. 2.5D and 3D models were tested in both study areas using four machine learning techniques: Cubist regression tree, Quantile Regression Forest (QRF), Artificial Neural Network (ANN), and 3D Generalised Additive Model (GAM). Results show that, in terms of R 2 and RMSE, 2.5D and 3D models using different machine learning models produce comparable results on the validation of depth interval observations. The 3D tree-based models produce "stepped" prediction of properties with depth. Results on the Hunter Valley area with point observations show that the 3D model cannot replicate field point observations. 3D soil mapping on point depth observation has lower accuracy and larger uncertainty compared to the 2.5D model. For future DSM studies, 3D soil mapping with depth as a covariate requires caution with respect to the prediction method and the requirements of the results.