 Thanks, everyone. I'm the PI for this project and James Houghton lead this project along with you know, Jennifer Edinburgh and the CH as a partners We have we are talking about interdisciplinary Interdisciplinarity we have a big team here. We have a range of experts including a soil scientist modellers data scientist social scientists all together we worked in this project and Before I go into this project, I would like to talk about what is the rationale for this project and what we have achieved What future look like for this? so So the rationale if you look at the we know that a climate change is the biggest threat The mankind is facing and we are all aware of the greenhouse gas emissions are responsible for that increase in greenhouse gas emissions If I look at the Scottish green house gas in inventory where we are operating from This is the situation in 2019 The agriculture sits at the third position third biggest emitter whereas a domestic transport and business are the first and second position There's a lot of investment is going on in several other sectors What is the situation in 2020? One agriculture slowly climbing up to the second position In fact, there is a very little progress was made in the last several last two decades in Reducing the greenhouse gas emissions from agriculture sector This is from several decades of data even though there are substantial reductions are achieved not from the agriculture sector This is lagging behind and these the Parliamentary report in Scotland specifically emphasizing on reducing the greenhouse gas emissions from agriculture sector So we can see overall it's only 1.1 percent increase Which is very modest and there is a lot of progress need to be done even across UK and if we want to achieve net zero all the sectors need to contribute and agriculture is not an exception and Agriculture is far lagging behind in the other sectors because there's several limitations associated with it One of the limitation is lack of credible and monitoring verification reporting system This is one of the limitation in achieving this So if you look at the background even though agriculture is a big source of climate and Greenhouse gas emission and also it's a great opportunity to see because the carbon and and there is a Technical potential for carbon sequestration is undisputable and there's a good consensus among the scientific community on this and these estimates will vary from study to study but overall there is a huge potential across in sequesting the carbon reducing the greenhouse gas emission and also Investing in agriculture and reducing the greenhouse gas in increasing carbon sequestration Actually provide a resilience to the system. That's a resilience to the food system, which is very important But one of the complications for this is soil organic carbon and the soil greenhouse gas emission Can cannot be easily measured which is a key barrier for implementing And achieving net zero So there are need for credible and reliable monitoring verification reporting system Especially for national reporting the way the national reporting is done is quite different from the way that is estimated Greenhouse gas emission is to measure the farm level This is going to pose problem as we go towards 2050 for the greenhouse gas emissions Estimations because we can declare the farm level. They are net zero at the national level They're not Again the national level they may declare as a net zero But at the farm level not because these methods are not aligned with each other So one of the aim for this project for is to what is the concept that look like if we align all these methods together Sorry, it's a jumping so and also one of the barrier for this is emission trading is completely jammed because of the lack of monitoring verification reporting system And also the track to a progress towards the net zero the farmers want to know How the farms are performing not now what is the direction? They are towards the net zero to when they reach 2050 if they adopt a management practice now How their emissions going to be by 2050? What is the direction of travel? Currently the market the whatever the tools available. They are not going to provide that information They provide only the current state what actually happening. So There is a clear gap here, which we need to fulfill. So that's the keeping that in mind bringing all that Digital technologies together we formulate the concept here where we can bring monitor at different scales using the sensors and process that information in near real-time and feed into the models by J cam for models and produce an output that could be used and guide the farmers and also Feed into the policy so We deployed sensors at two three different scales one is at the plot scale using the soil temperature my and also the other climate related sensors and also at the landscape level we use the drones to We run the drones to estimate the biomass of the crop so that we can estimate the carbon inputs into the soil and and also the national scale we have used the central in one and two we connected to the Google Drive Then we Looked at the management change what is happening really if the farmer of say that it's the Land is plowed. How can we validate that? Can we validate that information through the remote sensing? So that integration we we produce here So we integrate all the information not only that we integrated all the existing soil carbon and climate data For each land parcel level So what happens by this if we click on each land parcel we get all the information together What is the soil carbon stock with? Existing information how the climate going to be and what is the existing information associated with all the land parcel? So all we get together. So that's extremely powerful information in order to manage the lines So then we run this this one into the Model assembly. It's not one single model because if we use one single model There's a lot of conceptual uncertainty associated with it So we want to look at even the conceptual uncertainty So we use the peak in open source sift system and then embedded the DNDC, Baskara and Coast models and also we are intended to put more and more models as we go along currently three models are operating in this So we produce an output as I mentioned here. There are We are capturing the bio physical characteristic through the sensors But the still we need to know what's really happening on the ground for that we developed an app That's called the retina app. The app will interact with the end user. That's the farmer or the land managers We request them to input the land management information That means if they plow the land They just need to click one button so that we know that that particular land parcel is plowed and that information will Feedback into the system and keep the record of that and rerun the models Whenever there is a management intervention the whole system will read on and produce the output and immediately inform the farmer What is the impact so that we can influence their land management and also? Provide more information about how what the intended consequences of it So the app is used to provide the information to the farmers and also get the information Now the farmers are using a new software the muddy boots and others which farm management softwares If we we have in future plans to write an API so if we do that we don't ask any information to the farmer So it's all operate without taking any information from the farmer Collecting the bio physical information through the sensors and management information to the software so everything will be integrated So this is extremely useful for the many companies. They have a lot of forms in their supply chains They want to reduce their emissions They need an evidence and this tool can provide that evidence as we go along and it's scientifically It's very exciting because we can run the models iteratively several times And we learn about the system in a site specific manner So our models will get better and better as we go along more the system will operate and this will provide a unique opportunity in this case So overall how the system works we demonstrated this one two farms both are GM certain forms One is the cropline another is grassland. We deployed the sensors. We created a real-time dash dashboard You can see near our table. You can look at that and develop an app that app will kickstart run the models and integrate the other Information each land parcel level they get the information and also we doubt an algorithm where we guide the farmer for the soil Sampling and we can validate that information So I'm not going to talk more about this because you can come to the table and look at the app how that works so So what are the overall benefits for this? Retina technology is that it's quite interactive real-time model predictions and also complete data traceability Which is extremely important in terms of net zero and also the carbon markets if they want to we need to trace Where actually the carbon is currently that's not data collection directly from the field without Any input from the farmer as of now we are a little bit in but we want to bypass that in future Real-time data driven science bring more credibility and transparency the carbon markets Real-time data visualization for informations at the farm level And also we are using tier 3 models than that year to currently what are the tools in the market? These are tier 2 which is very average emission factors, which is not necessarily provides the right information at the field level So and also it's a payway to the digital twins in the next step We can read on the models and identify a tailored Management practice that gives the minimum emissions and higher yields because we are able to predict Whole carbon nitrogen flows in the system crop yields nitrogen dynamics and carbon dynamics that makes it the system very powerful So throughout this project we have four levels of engagement throughout this project So we have engaged with industries and there are several industries who are interested in Sheva brothers Nestle, Agri-Carbon, New Valley In fact, we are set up. We are setting up a field trials with them very soon and also singe enter and several other industries We had a talk split in this process and also in public engagement. We have a Royal Highland show We presented an arable Scotland. We have a farmers engagement around 200 farmers visited this one And we have engagement with them and a scientific community We have presented across several places and also we have follow-on funding Some of the things we have developed in this project led to follow-on funding that and also at the policy level I have given numerous presentations to the DEFRA and also still we are engaging with them in the soil team and others And also we have Scottish government. We work very closely with and this is a Scottish Minister who is very interested in rural development minister. They invested 51 million to the farmers there They can provide them. They can support the farmers for the soil sampling So we are trying to utilize our system how this will fit into the policy in that context. So This is in the picture of Mary Gusion who is the minister of rural affairs and Looking at the market and the demand associated with it We decided to launch this one as a spin-out company, which is called the carbon extras Which we applied for Scottish enterprise and we are successful and they identified this as a high-growth and spin-out Company and then supported currently into this So our vision is to create more Empowering the transition to the net zero and provide the support to the both industry and the farmers at the end And also we have six billion hectares in in the world the under farming And it is quite scalable. So there's a huge potential I think it's all about how we move forward and this in the next step. So In conclusion overall Retina fulfills the functions necessary for monitoring reporting and verification system to accelerate their efforts towards an edge zero and the data We we create to its policies is enormously useful and to the policy because we can anonymize this data and Provide inputs to the policy, which will be a real time. Currently. There's a huge lag In the data that come from the field to the policy So that lag can be substantially reduced through this one the approach will enable the data flow from the field to the end user And help real-time decision-making That's all from my side. Thank you very much