Offline Tumaini App is Here!
Dear Tumaini app users: We are happy to inform you that we already updated offline models for all the major banana diseases; please update the app at google play store. https://play.google.com/store/apps/details?id=ciat.cgiar.org.tumaini
Tumaini Gets more Acknowledgments
We are pleased to announce the publication of our paper Machine learning for high-throughput field phenotyping and image processing provides insight into the association of above and below-ground traits in cassava (Manihot esculenta Crantz)
Tumaini Gets more Acknowledgments
We are honored to share the latest Altmetric reports from Plant Methods, where two of our latest publications are mentioned here:
Tumaini Receives IT Award!
We are glad to announce the first prize of our Mobile App Tumaini, which was recognized by the government of Valle del Cauca as leader in digital transformation in the region. Congratulations!
Tumaini Gets more Acknowledgments
We are honored to announce that one of our latest papers “AI-powered banana diseases and pest detection” is rated as one of the top 5 most downloaded papers on 2019. Congrats team!
Phenomics Platform in CaliConf 2019
We congratulate Alejandro Vergara for his participation in CaliConf 2019, a group of conferences related to Agriculture and Food Security
Phenomics Platform in PyCon Colombia 2020
We congratulate our Research Assistant Alejandro Vergara who presented in the PyCon 2020
Phenomics Platform in Big Data Convention!
We congratulate to Dr. Selvaraj and Manuel Valderrama for their participation in Big Data Conference, hosted by ICRISAT in Hyderabad (India).
Nowadays analyzing the phenotype is frequently slower and more expensive than genomics due to the difficulties of measuring plant behavior at different levels and under different environements. Thus phenotyping becomes the limiting factor for plant biology and crop improvement. Our knowledge on the link between genotype and phenotype is currently hampered by insufficient capacity of the plant science community to analyze the existing genetic resources for their interaction with the environment. Advances in developing plant phenotyping methods and tools are therefore essential for success in characterizing shoot and root phenes to design next generation crops and forages as key components for climate-smart or eco-efficient agriculture.
Constraints in field phenotyping capability limit our ability to dissect the genetics of quantitative traits, particularly those related to yield, biotic and abiotic stress tolerance (e.g., yield potential, disease and insect resistance, drought, heat and water logging tolerance, and nutrient efficiency, etc.) and mitigation of climate change (increasing soil carbon accumulation and reducing methane and nitrous oxide emissions). The development of effective field-based phenomics platforms remains to be a bottleneck for future advances in genetic gain for yield and nutritional quality. However, progress in remote sensing technology and high-performance computing are paving the way.
The CIAT field Phenomics platform at CIAT-HQ is a state-of-the-art, high-tech facility comprised of automated rainout shelters (for drought screening) and low nitrogen field plots (for Nitrogen use efficiency screening) integrated with multi spectral imaging and Terrestrial Laser Scanning (TLS) system mounted on phenotowers, roof of rainout shelters and unmanned aerial vehicles (UAV). This automated, high-throughput platform allows repeated non-destructive image capture and multi-parametric analysis of small to medium sized field plots at multiple time points. CIAT phenotyping platform is also developing the capacity to estimate root yield in cassava using Ground Penetrating Radar (GPR) technology. The mounting of multi-spectral camera to a drone (UAV) can potentially harness the full capability of proximal sensing in a reliable, flexible, and efficient system that operates spatially at small to bigger plots. Combining this approach with environmental characterization as (Climate, soil and management status of the crop), with GPS positioning to spatially locate the proximal sensing data and with automated image analysis thus appears capable of delivering a robust field based phenomics platform.
We are also developing CIAT-Pheno-i, a scalable analytical framework, for robust aerial image processing especially breeder’s field focus. CIAT-Pheno-i handles different image sources (RGB, Multispectral and thermal) and satellite images helps to organize phenotypic data by retaining the metadata from the input in the result data set.
BANANA AI – TUMAINI MOBILE APP
Worldwide, banana production is affected by numerous diseases and pests. Around the world efforts are underway to develop a resistant export banana varieties, as well as research into just-in-time crop disease detection. However, the banana remains under-researched compared with the major crops in terms of digitalization. In this multidisciplinary research programme, we propose the integrative AI solution called Banana- AI, which consists robust machine will be made in partnership with Bioversity International (Africa) . The Algorithm for assaying works with both Machine and Mobile phones, and comes as a boon for millions of small holder farmers.
Cassava Root Phenomics Project- NSF grant: BREAD PHENO: High throughput phenotyping early stage root bulking in cassava using ground penetrating radar funded NSF –BREAD, USA, 2017 – 2019. At CIAT end, We are conducting & developing protocols for above and below ground phenotyping using remote sensing technology.
More cassava for less time
Cassava storage root phenotyping-BBSRC-GCRF: Screening of novel root traits for adaptation to nutrient deprivation in root crops”, under BBSRC- GCRF funds ( 2017 -2019). This project, a partnership with Dr. Tony Pridmore University of Nottingham (https://www.nottingham.ac.uk/research/groups/cvl/projects/gcrf.aspx) and the International Centre for Tropical Agriculture (CIAT) in Colombia, will develop the low-cost imaging and image analysis methods needed to recover quantitative 3D descriptions of cassava roots grown in an aeroponic environment. The complete system will be designed to allow easy replication throughout low and middle-income countries (LMICs), and will enable traits such as root volume to be measured and monitored.
UK SPACE AGENCY- ECOPROMIS
CIAT turns to space technology for monitoring crop performance
Ecopromis- UK SPACE Agency funded project : The project creates a Management Information System that will be used in oil palm and rice to help farmers adapt to climate change, reduce GHG emissions while improving productivity and profitability. Basic crop knowledge will be freely available through a web interface for the growers while Agricompas Inc. will provide commercial decision support to larger growers, processors, traders, financials and the government. This will create a sustainable income to sustain continued development and delivery of knowledge and decision support tools once the project has finished. 2018-2021, Country Lead, Colombia.
Field Drought phenotyping Project: Development of abiotic stress tolerant crops by DREB genes funded by MAFF, Japan, Phase II 2012-2018 As a crop physiologist in this project, conducting multi-location transgenic field trials and developing standard operating procedure to phenotype transgenic lines carrying DREB genes to enhance drought.
GENOME EDITING -BLB RICE
PHENOMICS PROJECT RICE
Phenomics Project in rice: Applying remote sensing tools for high-throughput phenotyping in rice to screening water and nitrogen use efficient rice varieties. Close Collaboration University of Tokyo & Texas A&M university to develop low cost high-throughput phenotyping tools funded by MOFA, SATREPS, JICA-JST, Borlaug research grand & CGIAR-US university linkage funding from USAID, 2016-2017.
NEWEST (nitrogen use efficient, water use efficient, and salt-tolerant)-USAID Project: project funded by USAID under Feed the Future initiative, 2014-2019. At CIAT, We are conducting & developing SOP for Transgenic field trials at Colombia and transfer protocols to other phenotyping team in Ghana, Nigeria & Uganda.
Drone is just a hardware device for plant phenotypers, but when it is linked with the precise and rapid analytics platform and well connected to the plant scientists (user), it jumps to feed the users with valued, useful and actionable data which eventually accelerate genetic gain – Michael Gomez Selvaraj.
Pheno i is a simple web based application to analyses drone and satellite images rapidly and give the decision support to plant breeders and farmers. Using this platform farmers can map the physical features of the farm to evaluate water flow, germination and productivity zones of their farms. Breeders can assess traits quickly such as plant height, canopy cover, biomass, nitrogen use efficiency, resistance to pest and diseases, canopy temperature etc. They have been validated this system to classify rice Hoja Blanca virus with collaboration with FLAR breeders and also using this application for precision agriculture project funded by UK Space Agency.
Tumaini Mobile App
TUMAINI mobile app is focused on banana farmers around the world (Collaboration between CIAT and Bioversity International). Using a large dataset of banana disease images taken in the field in Congo, Uganda & South India, we applied deep learning model to classify major banana diseases around the world. In addition to describing the type of disease, the app generates a series of recommendations and management of the detected problem. The app right now is trained for Banana but can be easily transferred to other CIAT mandatory crops.
Dr. Michael Gomez Selvaraj
Senior Scientist-Digital Agriculture, Leader Phenomics platform, Crop nutrition and health division - Alliance Bioversity International - CIAT
Km 17 Recta Cali-Palmira │C.P. 763537 │ A.A. 6713 Cali, Colombia
Email: firstname.lastname@example.org │ Phone +57 (2) 445 0100 Ext. 3652│Skype: micbiotech