The yield model value has risen from 167.85 to 168.60 bushels/acre, and appears to be converging to trend, which is currently at 169.46. The forecast has gotten much less bullish for corn in the past two weeks, largely due to a land-surface temperature catch-up that’s still taking place. As expected, the week-to-week variation looks more stable since more data came in. Note that the model yield is still bullish, since it’s below the trend and below the trade estimate/guess at 170 bushels/acre.
Gro’s yield model has updated from 162.46 to 167.85 bushels/acre in its second run of the 2017 corn season. The complexity of the modeling process makes it difficult to say exactly which factors caused the change, but we believe that rising land surface temperatures helped to boost model yield. Although 5.39 bushels/acre is quite a big increase for one week, 167.85 is still significantly below trend and last year’s yield. It remains bullish on corn prices relative to current expectations.
We don’t expect variation of this magnitude as the season goes on. Sensitivity to initial conditions is a common feature of complex models, and we are still close to the start of the season.
We don’t believe in bluffing or keeping things close to the vest. That’s why Gro is proud to announce the open release of our yield forecast model with performance that we believe equals or exceeds anything previously available at any price. We want to get rid of the black box mentality that’s kept such models proprietary to a few firms and secret from the many who need to use them. We are making our suite of machine learning and process models freely available on our website because we believe a transparent, fluid exchange of data and knowledge is the best way to answer the most pressing food and agricultural challenges facing us.
But this is just the start. Our modeling process not only performs well now, but is fully specified, generalizable, and constantly improving. During the growing season, forecasts are automatically updated on a weekly basis and available on Gro. Not only can you access our forecasts but you can also deconstruct and analyze the workings of each parameter used in the forecasts on a real time basis within Gro and can do so at a global scale within minutes. This was never possible before the launch of Gro.
The data used in the forecasts ranges from economic data and crop growing cycles to satellite imagery, weather data, and plant health measurements. We started with US corn, but we plan to roll out similar models for the entire world, even in areas with poor data availability, and for crops that are central to the agricultural ecosystem but currently attract little financial market interest. The forecast parameters are already available for analysis at global scale within Gro.
This will fly in the face of some long-held beliefs about how to do business. Regardless, the scientists and engineers at Gro are excited to contribute these findings to help to bring the proven benefits of cutting edge analytic methods to global agriculture.
A yield model capable of achieving a high level of accuracy months before the traditional window has enormous implications for food security, trade, and the global economy. The 2012 drought in the US led to record high prices for corn and a tragic increase in related hunger. When the record 2015 El Niño caused drought from India to Ethiopia, aid organizations scrambled to deal with potentially lethal local fallout. A model that could more quickly alert the global community to potential supply shortages would have eased the pressure. Food crises are happening more frequently due to population growth coupled with climate change. Any way to reduce that harm should be shared.
That’s why Gro’s yield model is being made available to the public. There will be continuous updates to increase accuracy and a community-based approach will further refine the model or identify areas of improvement. It’s a lesson learned from the citizen science movement and the technology industry: together, we can create something greater than any of us could alone.
Gro has developed a suite of machine learning-based models forecasting final corn yields. Each of those models generates a forecast. We then use a meta model based on our agronomic understanding of the plants in question to intelligently choose a weighting scheme for the sub-models. A key advantage to our approach is that we can optimize our predictive process to account for developments earlier in the season. We are able to better predict not only normal years but also anomalous years that lead to bumper harvests or drastic declines in yields. Gro’s full yield model updates at least every eight days and forecasts are made at the county level and aggregated to the national level. This compares favorably to the USDA’s and others’ monthly releases. As we incorporate new parameters and new data is generated for existing variables over time, the performance of our model relentlessly improves.
Yield models are traditionally either statistical or process-based. Pure statistical models operate strictly on historical data while process models attempt to use agronomic and ecological insights to make inferences that may not have been seen in the data previously. Each method has its quality-reducing limitations, which is why Gro’s yield model incorporates both.
The model was trained using verified historical yield data from the USDA’s approximately 1,500 growing counties. Numerous input data sources—including satellite-derived values of potential and actual evaporation of water from land and transpiration from plants (evapotranspiration), land surface temperature, and crop health measurements—were aggregated and weighted in a supervised machine learning process.
The resulting model features better anomaly and trend detection earlier in the season than the USDA’s official forecast. It achieves a high degree of accuracy even in very anomalous years. Running live through the 2016 growing season, the yield model predicted final yield for 2016 within 1.40% of the final yield by the end of August (final yield numbers are reported in January). In backtesting for the period 2001-2015, Gro’s model estimated national final yield with an average error of 2.69% by mid-August. When updated with 2016 data and backtested for the period 2001-2016, Gro’s model estimated national final yield with an average error of 2.44%. We were at least as good as, and in some cases better than, currently available private models available for purchase which provide no transparency into their methods to their users, let alone the broader public.
From our unique position within the global food and agriculture industry, Gro will foster collaboration between academic, commercial, and private interests. Every improvement made to the yield model will be publicly released and act as part of a continuous conversation leading to community-based innovation. The model will also always be running live within our product and all components of the model can be analyzed in real-time and deconstructed on a historical basis.
We all want to address food security, sustainability, and climate change concerns. By this public release, Gro is hoping to create a larger discussion regarding agriculture, demystify machine learning for the agricultural sector, and help people understand the role that fundamental scientific knowledge continues to play in our ability to accurately predict real-world outcomes. We sincerely hope that through honest and informed critique of our methods, we can further improve our already world-class model. This is where the greater community comes in. Tell us what we’re missing, help us to get better, and feel free to use the model for your own forecasts.
What Information Do We Collect?
The information we gather enables us to personalize, improve and continue to operate the Services. We collect the following types of information from our users.
IP Address Information and Other Information Collected Automatically:
· We automatically receive and record information from your web browser when you interact with the Services, including your IP address and cookie information. This information is used for fighting spam/malware and also to facilitate collection of data concerning your interaction with the Services (e.g., what links you have clicked on).
· Generally, the Services automatically collect usage information, such as the number and frequency of visitors to the Site. We may use this data in aggregate form, that is, as a statistical measure, but not in a manner that would identify you personally. This type of aggregate data enables us and third parties authorized by us to figure out how often individuals use parts of the Services so that we can analyze and improve them.
Information Collected Using Cookies:
· Most browsers have an option for turning off the cookie feature, which will prevent your browser from accepting new cookies, as well as (depending on the sophistication of your browser software) allowing you to decide on acceptance of each new cookie in a variety of ways.
We collect statistical information about how users collectively use the Services (“Aggregate Information”). Some of this information may be derived from Personal Information. This statistical information is not Personal Information and cannot be tied back to you or your web browser.
How, and With Whom, Is My Information Shared?
IP Address Information:
Information You Elect to Share:
We share Aggregate Information with our partners, service providers and other persons with whom we conduct business. We share this type of statistical data so that our partners can understand how and how often people use our Services and their services or websites, which facilitates improving both their services and how our Services interface with them. In addition, these third parties may share with us non-private, aggregated or otherwise non Personal Information about you that they have independently developed or acquired.
Information Shared with Our Agents:
We employ and contract with people and other entities that perform certain tasks on our behalf and who are under our control (our “Agents”). We may need to share Personal Information with our Agents in order to provide products or services to you. Unless we tell you differently, our Agents do not have any right to use Personal Information or other information we share with them beyond what is necessary to assist us. You hereby consent to our sharing of Personal Information with our Agents.
Information Disclosed Pursuant to Business Transfers:
In some cases, we may choose to buy or sell assets. In these types of transactions, user information is typically one of the transferred business assets. Moreover, if we, or substantially all of our assets, were acquired, or if we go out of business or enter bankruptcy, user information would be one of the assets that is transferred or acquired by a third party. You acknowledge that such transfers may occur, and that any acquirer of us or our assets may continue to use your Personal Information as set forth in this policy.
Information Disclosed for Our Protection and the Protection of Others:
Information We Share With Your Consent:
Except as set forth above, you will be notified when your Personal Information may be shared with third parties, and will be able to prevent the sharing of this information.
Is Information About Me Secure?
We store all of our information, including your IP address information, using industry-standard techniques. We do not guarantee or warrant that such techniques will prevent unauthorized access to information about you that we store, Personal Information or otherwise.
What Information of Mine Can I Access?
You can access and delete cookies through your web browser settings.
California Privacy Rights: Under California Civil Code sections 1798.83-1798.84, California residents are entitled to ask us for a notice identifying the categories of personal customer information which we share with our affiliates and/or third parties for marketing purposes, and providing contact information for such affiliates and/or third parties. If you are a California resident and would like a copy of this notice, please submit a written request to the following address: 12 E 49th Street, 11th Floor, New York, NY 10017
What If I Have Questions or Concerns?
If you have any questions or concerns regarding privacy using the Services, please send us a detailed message to email@example.com. We will make every effort to resolve your concerns.
Effective Date: March 11, 2014
b. You shall not (directly or indirectly):i. take any action that imposes or may impose (as determined by us in our sole discretion) an unreasonable or disproportionately large load on our (or our third party providers’) infrastructure; ii. interfere or attempt to interfere with the proper working of the Services or any activities conducted on the Services; iii. bypass, circumvent or attempt to bypass or circumvent any measures we may use to prevent or restrict access to the Services (or other accounts, computer systems or networks connected to the Services); iv. use manual or automated software, devices, or other processes to “crawl” or “spider” any page of the Site;
v. harvest or scrape any Content from the Services;
vi. otherwise take any action in violation of our guidelines and policies;vii. decipher, decompile, disassemble, reverse engineer or otherwise attempt to derive any source code or underlying ideas or algorithms of any part of the Services (including without limitation any application), except to the limited extent applicable laws specifically prohibit such restriction; viii. modify, translate, or otherwise create derivative works of any part of the Services; or ix. copy, rent, lease, distribute, or otherwise transfer any of the rights that you receive hereunder. c. We also reserve the right to access, read, preserve, and disclose any information as we reasonably believe is necessary to: i. satisfy any applicable law, regulation, legal process or governmental request; ii. enforce these Terms of Service, including investigation of potential violations hereof;
iii. detect, prevent, or otherwise address fraud, security or technical issues;
iv. respond to user support requests; or
v. protect the rights, property or safety of us, our users and the public.4. Third Party Services. The Services may permit you to link to other websites, services or resources on the Internet, and other websites, services or resources may contain links to the Services. When you access third party resources on the Internet, you do so at your own risk. These other resources are not under our control, and you acknowledge that we are not responsible or liable for the content, functions, accuracy, legality, appropriateness or any other aspect of such websites or resources. The inclusion of any such link does not imply our endorsement or any association between us and their operators. You further acknowledge and agree that we shall not be responsible or liable, directly or indirectly, for any damage or loss caused or alleged to be caused by or in connection with the use of or reliance on any such content, goods or services available on or through any such website or resource. 5. Termination. We may terminate your access to all or any part of the Services at any time, with or without cause, with or without notice, effective immediately. All provisions of these Terms of Service which by their nature should survive termination shall survive termination, including, without limitation, ownership provisions, warranty disclaimers, indemnity and limitations of liability. 6. Warranty Disclaimer. a. You release us from all liability for you having acquired or not acquired Content through the Services. We make no representations concerning any Content contained in or accessed through the Services, and we will not be responsible or liable for the accuracy, copyright compliance, or legality of material or Content contained in or accessed through the Services. b. THE SERVICES AND CONTENT ARE PROVIDED “AS IS”, “AS AVAILABLE” AND WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE, AND ANY WARRANTIES IMPLIED BY ANY COURSE OF PERFORMANCE OR USAGE OF TRADE, ALL OF WHICH ARE EXPRESSLY DISCLAIMED. WE, AND OUR DIRECTORS, EMPLOYEES, AGENTS, SUPPLIERS, PARTNERS AND CONTENT PROVIDERS DO NOT WARRANT THAT: (I) THE SERVICES WILL BE SECURE OR AVAILABLE AT ANY PARTICULAR TIME OR LOCATION; (II) ANY DEFECTS OR ERRORS WILL BE CORRECTED; (III) ANY CONTENT AVAILABLE AT OR THROUGH THE SERVICES IS FREE OF VIRUSES OR OTHER HARMFUL COMPONENTS; OR (IV) THE RESULTS OF USING THE SERVICES WILL MEET YOUR REQUIREMENTS. 7. Limitation of Liability. IN NO EVENT SHALL WE, NOR OUR DIRECTORS, EMPLOYEES, AGENTS, PARTNERS, SUPPLIERS OR CONTENT PROVIDERS, BE LIABLE UNDER CONTRACT, TORT, STRICT LIABILITY, NEGLIGENCE OR ANY OTHER LEGAL OR EQUITABLE THEORY WITH RESPECT TO THE SERVICES FOR ANY (I) LOST PROFITS, DATA LOSS, COST OF PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES, OR SPECIAL, INDIRECT, INCIDENTAL, PUNITIVE, COMPENSATORY OR CONSEQUENTIAL DAMAGES OF ANY KIND WHATSOEVER, SUBSTITUTE GOODS OR SERVICES (HOWEVER ARISING), (II) BUGS, VIRUSES, TROJAN HORSES, OR THE LIKE (REGARDLESS OF THE SOURCE OF ORIGINATION), OR (III) DIRECT DAMAGES IN EXCESS OF $50.00. 8. Governing Law and Jurisdiction. These Terms of Service shall be governed by and construed in accordance with the laws of the State of New York, including its conflicts of law rules, and the United States of America. You agree that any dispute arising from or relating to the subject matter of these Terms of Service shall be governed by the exclusive jurisdiction and venue of the state and Federal courts of New York County, New York. 9. Miscellaneous. a. Modification. We reserve the right, in our sole discretion, to modify or replace any of these Terms of Service, or change, suspend, or discontinue the Services at any time. Your continued use of the Services following notification of any changes to these Terms of Service constitutes acceptance of those changes. b. Entire Agreement and Severability. These Terms of Service are the entire agreement between you and us with respect to the Services, including use of the Site, and supersede all prior or contemporaneous communications and proposals (whether oral, written or electronic) between you and us with respect to the Services. If any provision of these Terms of Service is found to be unenforceable or invalid, that provision will be limited or eliminated to the minimum extent necessary so that these Terms of Service will otherwise remain in full force and effect and enforceable. The failure of either party to exercise in any respect any right provided for herein shall not be deemed a waiver of any further rights hereunder c. Force Majeure. We shall not be liable for any failure to perform our obligations hereunder where such failure results from any cause beyond our reasonable control, including, without limitation, mechanical, electronic or communications failure or degradation. d. Assignment. These Terms of Service are personal to you, and are not assignable, transferable or sublicensable by you except with our prior written consent. We may assign, transfer or delegate any of our rights and obligations hereunder without consent. e. Agency. No agency, partnership, joint venture, or employment relationship is created as a result of these Terms of Service and neither party has any authority of any kind to bind the other in any respect. f. Notices. Unless otherwise specified in these Term of Service, all notices under these Terms of Service will be in writing and will be deemed to have been duly given when received, if personally delivered or sent by certified or registered mail, return receipt requested; when receipt is electronically confirmed, if transmitted by facsimile or e-mail; or the day after it is sent, if sent for next day delivery by recognized overnight delivery service. Electronic notices should be sent to firstname.lastname@example.org g. No Waiver. Our failure to enforce any part of these Terms of Service shall not constitute a waiver of our right to later enforce that or any other part of these Terms of Service. Waiver of compliance in any particular instance does not mean that we will waive compliance in the future. In order for any waiver of compliance with these Terms of Service to be binding, we must provide you with written notice of such waiver through one of our authorized representatives. h. Headings. The section and paragraph headings in these Terms of Service are for convenience only and shall not affect their interpretation. Contact. You may contact us at the following address: 12 E 49th Street, 11th Floor, New York, NY 10017.