Which team will recrudesce the honest algorithm to enable a nursery to grow dwarf tomatoes independently ? That is the focus of this twelvemonth ’s Autonomous Greenhouse Challenge , a competitor organise by the Wageningen University & Research ( WUR ) Greenhouse Horticulture business whole . After the first part of the Challenge , five squad rest in the competition . The team that attain the most lucrative harvest of nanus tomato plant by mid - December using their algorithm will be the winners . Throughout the summer , the teams are working on their algorithm that will check the greenhouse from September .
farm crop in a greenhouse without human intervention . It sound like a utopia , but according to Stef Maree , datum research familiar at WUR Green Horticulture , it ’s not such an unrealistic medical prognosis . " greenhouse are getting increasingly ' smart ' . Different technologies already ensure that water system and nutrients are administered at the right fourth dimension and that an optimal temperature and humidness are maintain . datum collection also more and more enables growers to make better decision . This results in more efficient finish of crops . Which is very important , given the challenges we are face up such as increasing food demand , higher energy prices , carbon emission reduction and Labour Party shortages . "
WUR forerunner in autonomous cultivationAccording to Maree , WUR is one of the cosmos leaders in autonomous growth . " Within WUR , a turgid team of researchers is involved in various aspects of autonomous nursery growing , from figure to operation . One of the crowing labor we ’ve worked on in late years is AGROS . In this project , we showed that we can see cucumber refinement completely autonomously . Growing based on AI models and expert - based models produced results like to when growers controlled the greenhouse themselves . prove the hardheaded feasibleness is a Brobdingnagian discovery in independent growing . "
Autonomous Greenhouse ChallengeBesides through its own enquiry , WUR is also attempt to bring to the development of ego - operating glasshouse in other ways . For model , through the Autonomous Greenhouse Challenge . Maree explains what this competition aims to achieve . " Through the Challenge , we need to bring together people with different area of expertise from around the world . From plant experts to technology experts . It also bid participants a unique opportunity to gain hands - on experience with autonomous growing . test engineering in greenhouses is expensive . By making our inquiry greenhouses available , student , researcher and companies can test their tools for destitute and in a fun way . "
Growing dwarf tomatoesThis year will be the quaternary Autonomous Greenhouse Challenge . Every pinna , a dissimilar crop take on centre stage , says Maree . " This yr we chose the dwarf tomato . Unlike the plant life in previous challenges , this one is in pots and is sold as a whole plant . That in turn need new choice , because there is no unmarried autonomous scheme for every crop or nursery . The challenge is to deal the plant with both ripe and almost - ripe tomatoes , so consumer can watch the last tomatoes change by reversal flushed at home . We attempt to make the Challenge a petty more elaborate and unmanageable every year . For example , by creating less and less room for manual adjustment . We do that because greenhouses are also becoming increasingly more autonomous in pattern . "
First part completedA sum of 23 team from all over the public are taking part in the Challenge , the first part of which was completed in the outflow . The Challenge required the team to do unlike task . Maree : " The first task was to develop an algorithm or good example that they had to use to estimate the condition of a dwarf tomato flora based on a photograph . They also had to grow dwarf tomatoes virtually for two months . The last phase took spot on 6 and 7 June in Bleiswijk , where our research greenhouses are located . Here , the squad had to develop an algorithm for identify whitefly on chicken embarrassing trap in a hackathon . These flies can sham plant growth . It ’s therefore of import for cultivator to keep this pest under ascendency . "
Five teams compete for the winPart 1 of the Challenge finally bring on five teams who will compete for the win . These five teams have to get an algorithm that can control a greenhouse completely autonomously , Maree says . " Each team is give its own greenhouse in which they will have to grow and finally harvest dwarf Lycopersicon esculentum . In their algorithm , they can turn various buttons , such as water release , temperature , illumination and humidness . The conjuration is to find an optimum in this . More brightness level and passion intend you could harvest in the first place , but also that more energy is ingest . The glasshouse are equipped with standard sensors , but the team may fit extra sensors . "
Developing the algorithmThroughout the summer , the team are figure out on grow their algorithm . To do so , they are using a WUR simulator . Maree : " This simulator is a digital version of the tomato plant they will be maturate . We provided the simulator with data from a previous trial . During that trial , we produce gnome tomatoes in the same greenhouse , but manually . That intend we have a better approximation which parameters are authoritative for the crop to germinate and which sensors are needed for that . The team will build their algorithm all using this simulator . In practice , they then just need to fine - tune whether the greenhouse responds as they expect based on the simulation . "
Most lucrative crop winsThe algorithm must be quick on 2 September , says Maree : " After that , the greenhouse will need to do the rest of the oeuvre . Tomatoes must be harvested by 16 December . The winner is the squad with the high last net income . That count on the price per potful , the issue of deal worth selling and the cost incurred . We pre - arrange the damage per pot at 1.80 euro . Fewer than fair red fruit will mean the price is low , more red fruit means the price is gamy . Flavour also influences the price . We establish this on the dry subject mental object . The high this content , the more flavourful the tomato plant should be . "
worthful cognition and insightsApart from eternal celebrity , the winner also gains valuable cognition from the Challenge , sound out Maree . " They can habituate their algorithm for further inquiry or employ it operationally . Several successful businesses have emerged from former editions . For us too , the Challenge will bring new insight . For lesson , whether new sensors provide authentic data . But also which strategies will be most efficient . Because ultimately , that ’s the goal of self-directed farming . As an organiser , we do n’t see exactly how the algorithmic rule work , but we do see the consequences of choices . That in turning provides us with cargo of valuable data , which we will be able to use in further inquiry and to help the industry move towards fully autonomous greenhouses . "
Source : wur.nl
