Gabriel Tseng

Crop Yield Prediction USA results

1

Hi! Thanks for this collection of datasets and benchmark models. The [Crop Yield Prediction model ](https://sustainlab-group.github.io/sustainbench/leaderboard/#crop-yield-prediction) has very different yield values for the US and Brazil. For example, the test...

[WIP] Add an embedding layer for the months

1

As per Yasser's comments, replaces the one hot encoding with an embedding. ~Currently, the size of the embedding is fixed at 12, but if this works well this could become...

Add an unsupervised warm up for the models

1

Inspired by [tile2vec](https://arxiv.org/pdf/1805.02855.pdf), pretrains the models by training the models to make embeddings that are far away from each other more different than embeddings that are close to one another....

Memory Issue in the VHI preprocessor

1

Trying to preprocess all the VHI data leads to the process being killed: ``` Starting work on VHP.G04.C07.NJ.P1997031.VH.nc Killed ``` Looking into the logs of the google cloud instance indicates...

Validation vs. Test set for the burn scars dataset

1

Hello! Thank you for releasing these datasets. I understand that you use the "validation set" to report test results in the paper. It also seems like you use this set...

Hi - Thanks for this benchmark ! When I load tasks using `geobench.task_iterator`, I can pass a `benchmark_dir` which overrides the default benchmark directory when I load my tasks. However,...