Closed ZihengSun closed 5 years ago
@ZihengSun I've sent the proposal for review on your mail :smile:
@ZihengSun I have Updated The Proposal Added Some Things.Can you please go through it.I understand that at this point you might be flooded with reviewing proposals so make things simpler I have Highlighted Whatever Changes I Made So You wont have to Go through Entire Document.I really Hope That you can Give it One Final Read Before I submit on the portal tomorrow
@ZihengSun Should I give link to the Visualization Notebook Used in the proposal?
@ZihengSun I have submitted My Final Proposal To The GSoC Site After Modifying it according to your Last Feedback.I would Like To Thank You For Helping Me Out With the Proposals.And Will Continue Working On it Trying Various Ways And Communicating With You the results
@ZihengSun I have uploaded the final proposal. Please see other sections like training steps where I have delved deeper regarding eliminating overfitting, underfitting etc. Under current approach, I have added reasons why approach is not working and possible steps to eliminate the issues. I hope I have covered mathematically and logically the schedule. Thank you.
Thank you all for your efforts!
ESIP Member Organization
CSISS/LAITS, George Mason University Alaska Ocean Observing System (AOOS) and Axiom Data Science
Mentors
Ziheng Sun Jesse Lopez
Project Ideas
Ag-Net: building a customized deep neural network for recognizing crop categories based on spectral characteristics
Information for students
See ESIP general guidelines
Abstract
How many kinds of crops can you recognize? It is hard to say many. In most time of growing season, they are all green plants. Dent corn and sweet corn, black bean and red bean, barley and wheat, grass and weeds, etc. Distinguishing them takes a ton of knowledge and experiences. Agriculture scientists have struggled for years to figure out an automated way to recognize them. Deep learning is a powerful tool for non-linear classification problems. The critical part for deep learning is training dataset, which can be extracted from the reports and map products of U.S. department of agriculture. However, the existing deep neural networks are not performing as well as expected on crop classification because of their learned representation features in the back propagation are not common enough to tell the small differences among crops with similar external look. A customized network with special filters may help tell those minor differences in high spectral characteristics for more accurate recognition results.
Technical Details
Python; Keras; Geoweaver; numpy; scikit-learn; matplotlib; GDAL.
Helpful Experience
Machine learning knowledge; satellite image manipulation; python programming.
First steps
Start to get familiar with DeeplabV3, U-net or any other state-of-art deep neural network and test them on a sample training dataset.