Cloud-Based Decision Support and Automation for Precision Agriculture

With a growing population on the planet with request for better living standards, the demand for agriculture products, particularly specialty crops (fruits, nuts, vegetables etc), rises quickly. To meet this rising demand, farmers and researchers around the globe are exploring and applying new technologies to make agricultural operations more efficient and with better quality products. Precision farming is viewed as one of key technologies for addressing the rising demand for agriculture products. Precision farm enables farmers to operations for crops precisely based on their needs. Using information and engineering technology, precision agriculture measures and analyzes the conditions of a field and its environment, and uses this information to optimize field operations on-the-fly. Precision agriculture is essentially a data-driven operation: to accurately assess field conditions, a large amount of data need to be collected from multiple resources, e.g., infield sensors, weather stations, and remote imaginary, etc. These data need to be analyzed, and the results need to be applied to farming operations. At the core of today's precision farming operation are decision support systems (DSS) that analyze the data and recommend actions to farmers and growers.  

Collaborating with researchers at WSU Center for Precision and Automated Agricultural Systems (CPAAS), I developed a research program on cloud-based information systems for precision agriculture. The goal of this research is to develop a scalable and extensible information system that can provide real-time decision support in precision agriculture. We build the system on a could computing platform to provide scalability needed for processing a large volume of field data. To process data in various formats and from different devices, we are developing new data integration techniques. We are also experimenting and improving various data visualization techniques in context of precision agriculture. We successfully developed cloud-based decision support systems in areas of water management and labor/harvest management.

Our current research focus is on developing technologies and tool for next generation Decision Support and Automation System (DSAS). Compared with existing DSSs that are modeled after a human-in-the-loop decision process, the new DSAS features a fully automated decision process, from data acquisition, to data analysis and decision synthesis, to control field devices based on the recommended decision. We are developing technology that will make DSAS versatile, smarter, and fully automated. 

Appointment:

Affiliated appointment by the College of Agricultural, Human, and Natural Resources (CAHNR), Washington State University

Publications

  1. [TRW15] Li Tan, Ronald Haley, and Riley Wortman: "Cloud-Based Harvest Management System for Specialty Crops". Proceedings of IEEE 4th Symposium on Network Cloud Computing and Applications (IEEE NCCA'15), Munich, Germany. June, 2015.
  2. [STZZ14] Yongni Shao, Li Tan, Bolong Zeng, and Qin Zhang: "Canopy pruning grade classification based on fast Fourier transform and artificial neural network". Transactions of the American Society of Agricultural and Biological Engineers (ASABE). Volume 57(3). 2014.
  3. [TW14] Li Tan and Riley Wortman: "Cloud-based monitoring and analysis of yield efficiency in precision farming". Proceedings of 2014 IEEE Information Reuse and Integration (IEEE IRI'14). IEEE Press. San Francisco, CA. August, 2014.
  4. [TH+13] Li Tan, Ronald Haley, Riley Wortman, Yiannis Ampatzidis, and Matthew Whiting: "An Integrated Cloud-Based Platform for Labor Monitoring and Data Analysis in Precision Agriculture". Proceedings of 2013 IEEE Information Reuse and Integration (IEEE IRI'13). IEEE Press. San Francisco, CA. August, 2013.
  5. [AT+13] Yiannis Ampatzidis, Li Tan, Ronald Haley, Riley Wortman, and Matthew Whiting: "Harvest management information system for specialty crops". In the proceedings of annual meeting of ASABE, 2013.

Patent:

"Systems and Methods for Collecting and Accruing Labor Activity Data under Many-to-Many Employment Relation and with Distributed Access". Inventor: Li Tan. Assignee: Washington State University; United States Patent No. US 8,959,594 B2. Filed: Janary 28, 2013. Issued: February 17, 2015

Grants:

"Precision Canopy and Water Management of Specialty Crops through Sensor-Based Decision Making". USDA. $666,264. PIs: Qin Zhang, Li Tan, Whiting Matthew, and Troy Peters;

"A total systems approach to developing a sustainable, stem-free sweet cherry production, processing, and marketing system". USDA. $3,891,952.00; PIs: Matthew Whiting, Amit Dhingra, Manoj Karkee, Nnadozie Oraguzie, Carolyn Ross, Li Tan, and Qin Zhang.