Chrome Recommended
(only needed after submission)Today, efficient and cost-effective sensors as well as high performance computing technologies are looking to transform traditional plant-based agriculture into an efficient cyber-physical system. The easy availability of cheap, deployable, connected sensor technology has created an enormous opportunity to collect vast amount of data at varying spatial and temporal scales at both experimental and production agriculture levels. Therefore, both offline and real-time agricultural analytics that assimilates such heterogeneous data and provides automated, actionable information is a critical needed for sustainable and profitable agriculture.
Data analytics and decision-making for Agriculture has been a long-standing application area. The application of advanced machine learning methods to this critical societal need can be viewed as a transformative extension for the agriculture community. In this workshop, we intend to bring together academic and industrial researchers and practitioners in the fields of machine learning, data science and engineering, plant sciences and agriculture, in the collaborative effort of identifying and discussing major technical challenges and recent results related to machine learning-based approaches. This year the theme of the workshop will be Building Digital Twins for Ultra-precision Agriculture which will explore the recent advances in building virtual representations of plants, plots to fields using advances sensing, computational approaches, machine learning, scientific principles and domain knowledge. It will feature invited talks, oral/poster presentation of accepted papers, a machine learning competition and a panel discussion.
Registration Type | Attendance Type | Before 9/16 | After 9/16 |
---|---|---|---|
Student | In-Person Virtual |
$25 $15 |
$30 $20 |
Faculty | In-Person Virtual |
$50 $30 |
$75 $50 |
Industry | In-Person Virtual |
$200 $100 |
$250 $150 |
We invite extended 2-page-abstract for oral and/or poster presentations on topics Including but not limited to machine learning applications to plant phenotyping, plant pathology (e.g., disease scouting), plant breeding (e.g., yield prediction) and enabling smart farm management practices. We particularly encourage ML concepts applied to plant breeding, field-based experiments, production agriculture as well as lab based controlled experiments. We also encourage work that result in creating annotated benchmark datasets for ML in agriculture.
Select papers from the workshop will be published in the special issue of journal "Plant Phenomics".
Title: Scalable quantification of field-level agricultural carbon outcomes
Title: Modeling and Simulation Tools for Industrial and Societal Research Applications: Digital Twins and Genome-based Machine-learning
Title: 3D structural reconstruction of plants: A perspective from computer vision study
Day 1-1 America/Chicago Mon, 10 Oct 2022 08:00 ~ 12:00
|
Day 1-2 America/Chicago Mon, 10 Oct 2022 12:00 ~ 20:00
|
Day 2 America/Chicago Tue, 11 Oct 2022 08:00 ~ 12:00
|
---|---|---|
Breakfast/Welcome address | Lunch | Breakfast |
Prof. Fumio OKURA Osaka University |
Prof. Tarek ZOHDI University of California, Berkeley |
Prof. Koshizuka NOBORU Graduate School of Interdisciplinary Information Studies |
3 Contributed Talks | 3 Contributed Talks | 2 Contributed Talks and Competition winners |
Break | Coffee Poster sessions networking |
Break |
Prof. Zhenong JIN University of Minnesota |
Dinner with Jahmy HINDMAN CTO, John Deere |
Prof. Aarti SINGH Carnegie Mellon University |
3 Contributed talks | Start-up roundtable | |
Concluding remarks |
08:00-08:30
Breakfast/Welcome Address
08:30-09:00
Keynote 1: 3D structural reconstruction of plants: A perspective from computer vision study
Prof. Fumio OKURA
09:00-10:00
Contributed Talks
D1C1
Deep-learning in 3D from virtual plants for segmentation and completion tasks
David Colliaux (Sony CSL)*; Fabrice Besnard (ENS Lyon); Ayan Chaudhury (Indian Institute of Technology Kharagpur); Mona Sheikh Zeinoddin (Sony CSL); Peter Hanappe (Sony CSL Paris); Christophe Godin (INRIA Virtual Plants)
D1C2
Genetically driven autoencoders for trait quantification using hyperspectral leaf reflectance in a maize panel.
Michael Tross (University of Nebraska-Lincoln)*; Talukder Z. Jubery (Iowa State University); Anirudha A Powadi (Iowa State University); Yufeng Ge (University of Nebraska-Lincoln); Baskar Ganapathysubramanian (Iowa State University); James Schnable (University of Nebraska–Lincoln)
D1C3
Multi-Modal Aerial Mapping for Deep Learning-Based Phenotyping
Winnie Kuang (Carnegie Mellon University Robotics Institute)*; David Russell (Carnegie Mellon University); Francisco J Yandun (Carnegie Mellon University)
10:00-10:15
Break
10:15-11:00
Keynote 2: Scalable quantification of field-level agricultural carbon outcomes
Prof. Zhenong JIN
11:00-12:00
Contributed Talks
D1C4
Grape Cold Hardiness Prediction via Multi-Task Learning
Aseem Saxena (Oregon State University)*; Paola Pesantez-Cabrera (Washington State University); Rohan Ballapragada (Oregon State University); Kin-Ho Lam (Oregon State University); Markus Keller (Washington State University); Alan Fern (Oregon State University)
D1C5
Procedural generation of 3D maize models for LAI prediction
Ryan J Hoffman (Corteva Agriscience)*
D1C6
A self-supervised insect-pests detection app for precision agriculture
Shivani Chiranjeevi (Iowa State University)*; KOUSHIK NAGASUBRAMANIAN (Iowa State University); Matthew Carroll (Iowa State University); Sahishnu Hanumolu (South Fayette Township High School); Aditya Gupta (William Fremd High School); Talukder Zaki Jubery (Iowa State University); Soumik Sarkar (Iowa State University); Asheesh K. Singh (Iowa State University); Arti Singh (Iowa State University); Baskar Ganapathysubramanian (Iowa State University)
12:00-13:30
Lunch
13:30-14:15
Keynote 3: Modeling and Simulation Tools for Industrial and Societal Research Applications: Digital Twins and Genome-based Machine-learning
Prof. Tarek Zohdi
14:15-15:15
Contributed Talks
D1C7
Hierarchical Transfer Learning on Scaled-YOLOv4 for Insect Detection
Fateme Fotouhi (Iowa State University); Kevin Menke (Missouri University of Science and Technology); Aaron Prestholt (Iowa Soybean Association ); Ashish Gupta (Missouri University of Science and Technology, Rolla); Mattew Carroll (Iowa State University); Sajal K. Das (Missouri University of Science and Technology); Petro Kyveryga (Iowa State University); Baskar Ganapathysubramanian (Iowa State University); Arti Singh (Iowa State University); Asheesh K. Singh (Iowa State University); Soumik Sarkar (Iowa State University)*
D1C8
A small subset of genes can predict of complex trait with high accuracy in maize
Vladimir J Torres-Rodriguez (University of Nebraska-Lincoln)*; James Schnable (University of Nebraska–Lincoln)
D1C9
A Japan-Indo bilateral research project - Data science-based farming support system for sustainable crop production under climatic change
Seishi Ninomiya (The University of Tokyo)*
15:15-16:30
Coffee + Poster sessions + Networking
18:00-20:00
Dinner with Jahmy Hindman
08:00-08:30
Breakfast
08:30-09:00
Keynote 1: Data-Driven Solution and Agriculture
Prof. Koshizuka NOBORU
09:00-10:00
Contributed Talks + Competition Winners
D2C1
Quantifying the field-scale implications of natural variation in soybean leaf optical properties on carbon assimilation and water use
Darren T Drewry (Ohio State University)*
D2C2
Train deep learning-based plant phenotyping model with small dataset
Wei Guo (The University of Tokyo)*
CWT1
Competition Talk 1
Jiangsan Zhao
CWT2
Competition Talk 2
Michael Nawar
CWT3
Competition Talk 3
Zahra Khalilzadeh
10:00-10:15
Break
10:15-11:00
Keynote 2: AI enabled sequential decision making
Prof. Aarti Singh
11:00-11:45
Start-up roundtable
11:45-12:00
Concluding Remarks
Datasets will be made available here.
Participant teams must finalize their team members before the composition deadline is on August 15. teams joining after August 15 cannot change their team member composition during the competition phase. Prizes will be awarded to the winning teams. Funds will be paid in the most efficient manner, typically a check to winners living in the US with payment to each team member (up to 5 participants maximum). The team contact can suggest the distribution for the team members. If a team has more than five participants, five or fewer participants need to be identified to receive the prize money. For teams outside the US, prize money will be wired to a single individual representing the team. We will need full wire instructions in an appropriate format. Please note that there will be a wire fee on the receiving end of the transaction based on the recipient's bank/financial institution. At this time, we are unable to send wires to Iran, Cuba, North Korea, or Syria, therefore no prizes will be awarded there. Please note that prizes are tax reportable in the United States. Tax forms are required for payment recipients. US Citizens or permanent US residents: Form W9 including social security number and Foreign individuals: Form W-8BEN
Please use the discussion forum if you have any questions related to the challenge or contact us: mlcas2022challenge@gmail.com
Webpage managed by Timilehin Ayanlade, Iowa State University. For any concerns please contact ayanlade@iastate.edu
Powered by Github-Pages and Bootstrap4