Networked Society Symposium 2017: Today for Tomorrow – Interdisciplinary research for a sustainable future

“The science of today is the technology of tomorrow.”

– Edward Teller

If you googled Teller, you would find some controversial facts. However, that aside, Teller did capture, in his quote, the “power” that science has in shaping the world we live in tomorrow. A world that is increasingly, or might I say, already, immersed in technology. But “with great power comes great responsibility”, and it is in this light that the Networked Society Symposium 2017 (NSS’17) kicked off.

AL271343.jpg
Morning tea during the NSS’17. (Credit: Networked Society Symposium 2017)

The Digital Blue and Environmental Green

As individuals from different fields of research were seated in the B117 Theatre of the Melbourne School of Design, the stage was set for the “celebration” of interdisciplinary research. Interdisciplinary research that would have positive impacts and practical applications. As Professor Luciano Floridi, Director of the Digital Ethics Lab at Oxford Internet Institute, articulated, we, as the current generation, have the responsibility to build the foundations of a future society that future generations will be thankful for.

With the digital world, the features of our reality are being coupled, decoupled, and recoupled, or as we more commonly say, using the more “charged” term, disrupted. An example would be the decoupling of location and presence (Floridi, 2017). Whilst you physically enjoy a glass of Sauvignon Blanc at home, your interactions are with other users on a Facebook wine club page. Thus, your location is in Melbourne, but your presence is online, and your reach is global. This is just a simple example of how technology is “cleaving” at the features of our reality.

However, as we delved deeper “into the seeds of time”, it has not just been the clear-cut prediction of “which grain will grow and which will not” (Macbeth, 1.3.159-162). Instead, the “weeds’ of uncertainty and challenges have also surfaced. Predominantly, the deterioration of our environment in the face of climate change, and how we would shape our digital world with it. As such, how can we nurture the desirable and neutralise the undesirable?

Nurturing the desirable: Urban Green Spaces

With climate change, Australia is experiencing more frequent and hotter “hot days”, with heat waves increasing in duration, frequency, and intensity (CSIRO & Bureau of Meteorology, 2015). As such, Urban Green Spaces have become crucial in cooling urban heat islands and providing refuge against harmful air pollutants or the “concrete jungle” itself.

At NSS’17, interdisciplinary research on Urban Green Spaces involved technologies such as sensor networks, remote sensing cameras, and social media. Sensor networks were able to detect “microclimate” changes in temperature, humidity, and solar radiation, between grey (concrete) and green (greenery) areas. Furthermore, remote sensing cameras, mounted onto vehicles, yielded real-time thermal and visible images, that would be used in monitoring tree-health in city centres. And with social media, an analysis of positive and negative sentiments “tweeted” by Twitter users at existing Urban Green Spaces, indicated the influence of these spaces on human wellbeing. Thus, with these, the existence of Urban Green Spaces can be justified as beneficial, and the nurturing of desirable designs can be enhanced and propagated effectively alongside urbanisation.

Nurturing the desirable: Digital Vineyards

Besides Urban Green Spaces, interdisciplinary research has also yielded how technology can transform the agriculture industry for the better. This is seen in the development of “digital vineyards” to combat smoke contamination in vineyards as a result of increased bush fires in Victoria, Australia. With bush fires now occurring from October to March, smoke contamination in vineyards are on the rise. And with the accumulation of smoke-related compounds, known as guaiacol glycoconjugates, in grapes, these compounds are resulting in undesirable aromas and flavours in wine, thereby reducing their value (Fuentes & Tongson, 2017).

OLYMPUS DIGITAL CAMERA
Dr Sigfredo Fuentes putting the use of “digital vineyards” into context. (Credit: Networked Society Symposium 2017)

As such, by combining the use of Unmanned Aerial Vehicles (UAVs) and remote sensing with agricultural science, real-time Infrared Thermography Imaging (IRTI) would be able to recognise smoke contaminated vineyard canopies by detecting pattern changes in leaf conductance. The presence of smoke-related compounds in berries could also be detected using non-invasive Near Infrared Spectroscopy (NIR), which determines the composition of berries. Thus, as Dr Sigfredo Fuentes, Senior Lecturer in Wine Science at the University of Melbourne, presented, smoke-contaminated areas could be mapped and differential harvesting could occur.

Remote Sensing Figure 3
A diagram representing how UAVs and remote sensing can be used to detect smoke contamination in vineyards (Fuentes & Tongson, 2017).

Neutralising the undesirable: Getting it “right”

Whilst digital vineyards are viewed as a solution to bush fire smoke contamination, other areas of fundamental industries, such as law, are facing “warning signs” of undesirable outcomes. Particularly in “how” we will regulate the access to law without the actual access to lawyers. And with the adoption of open data, “how” we will adapt to the use of it, especially with increasing concerns over data privacy.

But if done “right”, in terms of enhancing the “human” in our digital projects, whereby the technologies we build are “open, tolerant, equitable, just, and supportive” for both humans and the environment to flourish, the digital world can be for the better (Floridi, 2017). And as I once asked an 83 year old man on “what not to do in life”, he quoted Charles Dickens’ “a heart that never hardens, a temper that never tires, and a touch that never hurts”. Perhaps what we need then, is technology that would never harden our humanity, nor tire ourselves from bettering our designs, and most importantly, technology that would never hurt ourselves. With this, the NSS’17 concluded with the mindset for design to be for the long-term sustainability of humans in the digital world.


References

Floridi, L. Philos. Technol. (2017) 30: 123. https://doi.org/10.1007/s13347-017-0259-1

CSIRO and Bureau of Meteorology 2015, Climate Change in Australia Information for Australia’s Natural Resource Management Regions: Technical Report, CSIRO and Bureau of Meteorology, Australia

Fuentes, S. and Tongson, E., 2017. Vineyard technology: Advances in smoke contamination detection systems for grapevine canopies and berries. Wine & Viticulture Journal, 32(3), p.36.

University of Melbourne’s Dookie Day 2017: The Future of Food in Technology

IMG_2954(1)

Bus rides are made for silently collecting one’s thoughts or taking a good nap. But as the bus drove from Melbourne’s CBD, up north to Dookie, I had questions. Who would turn up? And for those that did, how would they react to the latest developments in technology for agriculture?

Drones for agriculture

At Dookie Day, drones were showcased for agriculture. This stemmed from the University of Melbourne’s (UoM) collaboration with XM2, pioneers in the Unmanned Aerial Vehicle (UAV) market, to develop the Melbourne Unmanned Aircraft Systems Integration Platform (MUASIP). Thus, MUASIP is a platform that facilitates data capture using UAVs and the data is processed meaningfully for research and commercial applications. Think of it as the “spine” that would support the “body” of functions and capabilities.

At the moment, we have projects in precision viticulture, whereby wine growers are able to use UAVs to collect data on how grapevine canopies are affected by abiotic and biotic stressors (Baofeng et al., 2016). This would enable informed decision-making on irrigation schedules, fertiliser usage, and overall vineyard management, as inspections can be highly spatial or on a plant-by-plant basis. However, as Dr Sigfredo Fuentes, a UoM Senior Lecturer in Wine Science, highlights, “the end goal is the incorporation of technology in food security”. As such, the work on using drones in viticulture would one day be transferable to other farming systems too.

IMG_2937(1)
XM2’s DJI Inspire 1 drone used in the demonstration.

For the actual demonstration, we had XM2 demonstrate their DJI Inspire 1 drone. And true to its popularity, the presence of the drone itself, it attracted both the young and old. For this demonstration, the drone was modified to capture thermal data, whereby different materials would show different temperature patterns. The application of this would, for example, enable a farmer to determine the moisture level of his or her field, thereby knowing how well irrigated it is. This is important, especially in the face of climate change, as the rapid detection of “stressed” crops between a day or 16 days (if satellite maps are used) can be the determining factor in yield and quality.

IMG_2972(1)
Prep-school kids observing the drone application.

Decoding “us” the consumer

Whilst the use of drones are on the “growth” side, technology also has a place in “sensory science”. At Dookie Day, a BIOSENSORY “face reader” application was on demonstration. It was developed to decode consumer behaviour associated with unconscious responses. For example, whether you “frowned” upon tasting a piece of cheese. The “magic” of the face reader is that it captures food and taste preferences, expressed through facial expressions, which may be omitted from using, say, the traditional questionnaire (Fuentes et al., 2015). And the application is also capable of monitoring your heart-rate and body temperature.

IMG_2952(1)
The BIOSENSORY application in action.

Imagine being able to quantify the actual “emotions” associated with tasting chocolate. I would buy a variety of chocolate, set myself in front of the application, and taste test the different chocolates I bought, to find “the One” that brought me the most happiness. But on a more professional note, this technology is highly valuable to food companies, such as those in the chocolate, wine, cheese, or even beer industry. The BIOSENSORY application would provide consumer insight to pinpoint where the opportunities for food companies are at.

At the end of the day

Although the existence of certain technologies in the agricultural industry is common knowledge, its mainstream adoption is a different story. The reasons may be cultural in origin, or perhaps it is because of the idea that there is “no” support system.

However, at Dookie Day, questions were asked and answers were given. Answers in the form of MUASIP, which addressed the need to have an integrated support system for the transference of UAV system know-hows. Answers in terms of the benefits of using the BIOSENSORY application that would improve testing and our understanding of ourselves as consumers. Answers in the form of people responding positively and wanting to participate in the latest developments of agriculture; from young children and students, to the “veterans” of the farming industry.

IMG_2999(1)
Dr Sigfredo Fuentes being interviewed.

There will be more questions as new technologies emerge. But questions, in combination with informative and applicable answers, can become starting points for greater understanding and acceptance. And that is what Dookie Day was for.


References

Baofeng, S., Jinru, X., Chunyu, X., Yulin, F., Yuyang, S. and Fuentes, S., 2016. Digital surface model applied to unmanned aerial vehicle based photogrammetry to assess potential biotic or abiotic effects on grapevine canopies. International Journal of Agricultural and Biological Engineering, 9(6), p.119.

Fuentes, S., Torrico, D., Talbo, M., Gonzalez-Viejo, C., Moore, S., Kashima, Y. and Dunshea, F., 2015. Development of a Novel App for Sensory Analysis of Food and Beverages using Biometrics from Video and Image Analysis.

New Paper: Assessment of beer quality based on foamability and chemical composition using computer vision algorithms, near infrared spectroscopy and artificial neural networks modelling techniques

By

Claudia Gonzalez Viejo 1, Sigfredo Fuentes 1*, Damir Torrico1, Kate Howell1, and Frank R. Dunshea1.

1 University of Melbourne, School of Agriculture and Food, Faculty of Veterinary and Agricultural Sciences, VIC 3010, Australia

* Correspondence: sfuentes@unimelb.edu.au; Tel.: +61 3 9035 9670

Journal of The Science of Food and Agriculture

Full Article: CLICK HERE

ABSTRACT:

Beer quality is mainly defined by its color, foamability and foam stability, which are influenced by the chemical composition of the product such as proteins, carbohydrates, pH and alcohol. Traditional methods to assess specific chemical compounds are usually time-consuming and costly. This study used rapid methods to evaluate 15 foam and color-related parameters using a robotic pourer (RoboBEER) and chemical fingerprinting using near infrared spectrometry (NIR) from six replicates of 21 beers from three types of fermentation. Results from NIR were used to create partial least squares regression (PLS) and artificial neural networks (ANN) models to predict four chemometrics such as pH, alcohol, Brix and maximum volume of foam.

NIRANN

Invited Speaker: 10th International Symposium on Viticulture and Oenology 2017

Dr Sigfredo Fuentes has been invited to the 10th International Symposium on Viticulture and Oenology to be held in Wuzhong, Ningxia – China from the 20th to the 22nd of April 2017.

Presentation: Detection of berry cell death and smoke contamination in berries using near infrared spectroscopy and machine learning algorithms.

Why there are more and bigger bushfires?: Smoke Taint in Berries and Wine, What can we do about it?

Non-invasive smoke-taint detection in berries from grapevine (Vitis vinifera L.) using near infrared spectroscopy and machine learning models

I have been spending some whole nighters working on this topic due to recent news about extensive bush fires in Chile and in New South Wales, in January and February 2017 respectively. Both of these events have been named by the media as the biggest bush fire events in their respective histories. In Chile, the majority of the bush fires were in the central part of Chile, coincidentally to the majority of grapevine plantations. We do know that smoke taint has the biggest effect on berry contamination after veraison (7 days after on-set), which was about the timing of bushfires for a few cultivars for both Chile and NSW.

smoke-taintnsw2

smoke-taint-chile

A recent report (February 2017) from the Victorian Government – Australia, has concluded that bush fires will increase severity and the window of opportunity due to climate change, specifically due to increases in temperature, increased frequency and intensity of heat waves and drought events.

smoke-taint-report

So, what can we do about it?

As said before, I started to dig up some data from an ARC – Linkage project in which I worked as part of a team from The University of Adelaide. In that project we smoked artificially a number of cultivars to see the physiological effects of smoke contamination. From the canopy perspective and stomatal conductance, to be more specific, this effect can be explained through the chemical reaction between the main compounds found in smoke: carbon dioxide (CO2) and carbon monoxide (CO) and water. When getting in contact with stomata, smoke gases they can pass to the sub-stomata cavity, which is at 100% relative humidity. These compounds are then mixed with water forming carbonic acid (H2CO3) which reduced pH (acidic) hence close stomata.

This effect was reported in a poster in which I did a model to detect this effect on stomata conductance to discriminate canopies that have been contaminated or not with smoke. See posting by clicking here. The models worked really well for all the cultivars studied but Sauvignon blanc. I did attributed this effect to the morphology of leaves for this cultivar, which have high pubescence in the abaxial side. My hypothesis was that this offers a barrier to smoke, which can explain the inefficiency of the model based on the lack of stomatal conductance reduction.

I am currently working in the development of these models considering the top of canopies to apply them using infrared thermal imagery from Unmanned Aerial Vehicles (UAV), which can map a whole vineyard in the days after a bush fire event.

After the bush fires in Chile, I have revisited the Near Infrared (NIR) data from berries to see whether I was able to generate machine learning models to detect smoke taint in berries triggering the instrument around the skin and then measuring also in halved berries. The instrument that we used was a ASD FieldSpec® 3, Analytical Spectral Devices, Boulder, Colorado, USA. Which measures in the range of 350 – 1880 nm.

smoke-taintnir

I have decided to concentrate the models in the700 – 1100 nm range using the second derivative of data, since it is the range of inexpensive NIR instrumentation. Also, after analysis of the rest of the wavelength range, the improvements of models obtained did not justified the jump in price of instrumentation from around $2,000 – $3000 to $38,000 – $65,000.

I did obtain three interesting models, the first was to detect whether the berries measured in a bunch have been contaminated or not using Artificial Neural Networks. I tried with data from whole and half berries and surprisingly I got better results with full berries. This is important since it renders the methodology as non-invasive. And makes sense when reading reports which found that the majority of glycocongugates are found in the skin of berries, which are higher than the pulp and higher that those found in seeds.

smoke-taint-m1

Then I tried models using machine learning fitting algorithms to see whether I could predict the levels of glycocongugates in the berries (whole):

smoke-taint-m3

And finally, whether I was able to predict smoke taint compounds in the wine made with contaminated and non contaminated berries, such as guaiacol, Syringol and cresols:

smoke-taintcompoundsnew

 

These are very exciting preliminary results which I am in the process of writing up for a peer review publication. The best thing is that if measurements made in the field are associated to GPS tagging, this could produce a contamination map using simple kriging interpolation techniques. This tool can support the decision making process towards differential harvest to avoid contaminating the whole production and salvaging fruit that has not been contaminated to the levels of spoilage. It offers also alternatives for winemaking to avoid excessive crushing and fermentation with skins that could contribute to the increase of smoke taint compounds in the final wine. Decisions can also be made by assessing the timing of ageing in barrels and whether it is required at all. And obviously, making non-contaminated wine using non-contaminated fruit. As can be seen in my preliminary results, the model for glycocongugates rendered a 10% error, which by quantifying the levels of smoke taint compounds does not make much difference in the final wine and it may contribute even to increased organoleptic characteristics with tones of leather, wood, bacon, etc

Something to look forward after all these tragedies.

Dr Sigfredo Fuentes

The University of Melbourne