{"id":2943,"date":"2017-01-18T23:06:56","date_gmt":"2017-01-18T23:06:56","guid":{"rendered":"https:\/\/www.rsoftsolution.com\/blog\/telluslabs-wants-to-help-us-better-understand-our-planet.html"},"modified":"2017-01-18T23:06:56","modified_gmt":"2017-01-18T23:06:56","slug":"telluslabs-wants-to-help-us-better-understand-our-planet","status":"publish","type":"post","link":"https:\/\/www.rbsitsoftwaresolution.in\/blog\/telluslabs-wants-to-help-us-better-understand-our-planet.html","title":{"rendered":"TellusLabs wants to help us better understand our planet"},"content":{"rendered":"


\n<\/p>\n

If you\u2019ve spent time following companies like Orbital Insight<\/a> and\u00a0Descartes Labs<\/a>, you might assume the geospatial analytics race\u00a0has been won. But TellusLabs<\/a> thinks, on the contrary, that the table hasn\u2019t even started to cool. Armed with $3 million in new seed funding from IA Ventures<\/a>\u00a0and an investor group including Hyperplane VC<\/a>, FounderCollective<\/a> and Project11<\/a>, the Boston-based startup wants its trust in the nexus of human intuition and machine intelligence to be the ace that wins it a seat at the table and more.<\/p>\n

\u201cGeospatial analytics\u201d is simply a fancy way of saying that these companies gather information by analyzing satellite images. And oh\u00a0are people pulling crazy things from satellite images these days. Using trigonometry and shipping containers to estimate oil supply, prognosticating on financial returns by analyzing the number of cars in big box mart parking lots, and even surveying\u00a0demolished houses after storms.<\/p>\n

But\u00a0TellusLabs is perfectly content slogging it along predicting corn and soybean output.\u00a0They also happen to be pretty good at it. The team\u2019s initial beta, a model with daily forecasts for the two crops ended the year at the exact USDA estimate for soy and within 1 percent of the USDA estimate for corn \u2014 no small feat.<\/p>\n

The value in that accuracy is about more than numbers. It\u2019s about efficiency and granularity. TellusLabs will hit its stride if its able to provide local insights more quickly than competitors.<\/p>\n

\"screen-shot-2017-01-16-at-9-14-16-pm\"<\/p>\n

TellusLabs and the USDA converge at the end of the year.<\/p>\n

Despite a successful beta, there\u2019s still plenty of room to question the startup\u2019s\u00a0approach.\u00a0TellusLabs doesn\u2019t own the rights to any imaging hardware, the company isn\u2019t using any proprietary data for its models and its avoiding popular additions like\u00a0deep learning.<\/p>\n

Instead,\u00a0the company is relying on a variety of medium and coarse resolution satellites plus ground-truth including a 15-year-old satellite called the Moderate-Resolution Imaging Spectroradiometer or MODIS for short. Company CEO David Potere insists\u00a0it\u2019s not sexy but it gets the job done.<\/p>\n

\u201cInside each pixel we capture 36 spectral bands at various spatial resolutions,\u201d explains Potere. \u201cWe see ourselves as radiologists.\u201d<\/p>\n

The NASA data sets that TellusLabs is using are updated multiple times per day. The tradeoff is that the images captured are of much lower quality. Other sources of imagery don\u2019t\u00a0offer as much consistency or historical depth.<\/p>\n

One of the biggest trends in space right now is the rise of the cube satellite. But popularity aside, Potere believes it will be 5-7 years before enough data exists for building reliable models and before a clean data pipeline exists for the imagery.<\/p>\n

\u201cWe don\u2019t have an exciting new deep learning algorithm but we are in the trenches building clean features every day,\u201d explains Potere. \u201cThat clean feature database is just essential. It really is garbage in, garbage out.\u201d<\/p>\n

\"lc80630462016040lgn00_bands_753_tif\"<\/p>\n

Agriculture, cooled lava flows, and rainforest in Maui, Hawaii, USA<\/p>\n

The company is very clear that it\u2019s building a geospatial analytics tool and not an AI stack that could do facial recognition with the flick of a switch.\u00a0The team\u2019s idea is to avoid\u00a0a large amount of extrapolation from an everything-but-the-kitchen-sink approach to data.<\/p>\n

\u201cWe think we know something about plant biology, about how corn and soy grows, so why ignore that\u201d adds\u00a0Potere.<\/p>\n

An apt metaphor would be whiskey distilling. Nobody would blink an eye if a master distiller, waiting for his own product to mature, sold a curated mixture of second-hand\u00a0products. Potere argues, essentially, that the\u00a0same is true for the nascent geospatial analytics space.<\/p>\n

\u201cWe\u2019re not luddites about drones or high resolution imagery,\u201d continues\u00a0Potere.<\/p>\n

In the meantime, Tellus\u2019 competitors are locking down partnerships with wheelers and dealers of satellite imagery. DigitalGlobe is providing\u00a0Orbital Insight<\/a> with hundreds of terabytes of high resolution imagery and Planet Labs is getting cozy with\u00a0Descartes Labs.<\/a><\/p>\n

Across the industry, a lot of Tellus\u2019 competitors are eager to provide insights on everything the light touches: forestry, water, industrial monitoring \u2014 the list goes on.<\/p>\n

Corn and Soy were\u00a0a natural starting point for everyone. It\u2019s economically critical meaning people will pay for it and the USDA\u2019s historical data is about as good of a training set as any enterprising machine learning developer can find.\u00a0The challenge for everyone is going to be finding focus and \u00a0revenue at the same time.<\/p>\n

<\/p>\n

Article source: http:\/\/feedproxy.google.com\/~r\/techcrunchIt\/~3\/NOnczoJaxFc\/<\/p>","protected":false},"excerpt":{"rendered":"

If you\u2019ve spent time following companies like Orbital Insight and\u00a0Descartes Labs, you might assume the geospatial analytics race\u00a0has been won. But TellusLabs thinks, on the contrary, that the table hasn\u2019t <\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[19],"tags":[25],"class_list":["post-2943","post","type-post","status-publish","format-standard","hentry","category-enterprise-software","tag-enterprise"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t