A team led by CABBI Director Andrew Leakey & Postdoc Sebastian Varela created a machine-learning tool that can teach itself to differentiate between aerial images of flowering & nonflowering grasses—greatly accelerating agricultural field research.
News ➡️https://t.co/JhnCBjekcb
CABBI researchers combined machine learning & 3-D drone imaging to create a powerful new tool to measure growth in #miscanthus.
The result is a faster and cheaper way to evaluate the most promising varieties of this next-generation #bioenergy crop! 🌱
➡️ https://t.co/mCzd1KrCdT
A new study by CABBI #Feedstock Production & #Sustainability researchers shows that using spatio-temporal 3D-convolution neural networks & UAV time series imagery helped rapidly predict lodging damage in sorghum & could enhance field plant phenotyping.
📰https://t.co/DvxHb2HtoF
We're celebrating the International Day of Women and Girls in Science!
Let's look back on the life of Marie Skłodowska Curie: a Nobel Prize laureate who dedicated her life to science and became one of the world's greatest scientists.
#WomenInScience#NobelPrize
SUMMER INTERNSHIP OPPORTUNITY!
Join us for RISE, our paid summer internship program in bioenergy research!🌱🔬
We are seeking undergrads nationwide from underrepresented groups to work with research mentors!
🔶 Deadline to apply: Feb. 24
Learn more!➡️ https://t.co/7DEcq3QKeH
Happy to share new machine-learning, UAV, high-throughput phenotyping study on lodging in biomass sorghum demonstrating the power of 3D-CNN and time-course data https://t.co/q4MkX7opis @CABBIbio @iBioIllinois @IllinoisCropSci@IGBIllinois@NAPPN_org
#Landsat 9 data is officially available to the public! Since the satellite launched, there have been many steps before we could call it fully operational. ⬇️ [1/5]
A #CABBI study led by @pixelvar79 used high temporal resolution images from drones to understand the relative importance of dynamic and static information throughout the season to predict final above-ground biomass for sorghum. This could benefit work to improve bioenergy crops.
Check out our new article @KSUCROPS #mdpiremotesensing Early-Season Stand Count Determination in Corn via Integration of Imagery from Unmanned Aerial Systems (UAS) and Supervised Learning Techniques https://t.co/KYiWACcX51 @RemoteSens_MDPI