Dust-model-dichotomous-performance-analysis

Using a collated dataset of >90,000 dust point source observations from 9 drylands studies from around the world to assess the performance of dust emission models. Here we use the albedo-based dust emission model developed by Chappell and Webb (2016) in Google Earth Engine. The outputs from each DPS location are standardised and analysed in Python to describe the dichotomous coincidence of observed dust emission with model simulation. Discussion topics are developed from the empirical cumulative distribution function (ECDF) of wind shear velocity conditions during observed dust emission days and all days. These ECDF are also produced in Python.

Link to Google Earth Engine code (Google user account and login required): https://code.earthengine.google.com/a48652d123f7c56dab0bcdf4a3f9abf5

Includes two folders:

Dust Point Source (DPS) observation data, including co-ordinates, dates of observation, and 1-degree grid id
Look-up-tables (LUT) required to run Python code

Dust model dichotomous performance analysis

Related tags

Overview

Dust-model-dichotomous-performance-analysis

Owner

BERTAC (BERT-style transformer-based language model with Adversarially pretrained Convolutional neural network)

This project deals with a simplified version of a more general problem of Aspect Based Sentiment Analysis.

A deep learning-based translation library built on Huggingface transformers

:id: A python library for accurate and scalable fuzzy matching, record deduplication and entity-resolution.

Korean stereoypte detector with TUNiB-Electra and K-StereoSet

Code for "Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments".

Composed Image Retrieval using Pretrained LANguage Transformers (CIRPLANT)

Enterprise Scale NLP with Hugging Face & SageMaker Workshop series

A Pytorch implementation of "Splitter: Learning Node Representations that Capture Multiple Social Contexts" (WWW 2019).

Torchrecipes provides a set of reproduci-able, re-usable, ready-to-run RECIPES for training different types of models, across multiple domains, on PyTorch Lightning.

Contract Understanding Atticus Dataset

MILES is a multilingual text simplifier inspired by LSBert - A BERT-based lexical simplification approach proposed in 2018. Unlike LSBert, MILES uses the bert-base-multilingual-uncased model, as well as simple language-agnostic approaches to complex word identification (CWI) and candidate ranking.

Extract city and country mentions from Text like GeoText without regex, but FlashText, a Aho-Corasick implementation.

An open-source NLP library: fast text cleaning and preprocessing.

Let Xiao Ai speakers control third-party devices

Neural text generators like the GPT models promise a general-purpose means of manipulating texts.

ALIbaba's Collection of Encoder-decoders from MinD (Machine IntelligeNce of Damo) Lab

A minimal code for fairseq vq-wav2vec model inference.

[EMNLP 2021] Mirror-BERT: Converting Pretrained Language Models to universal text encoders without labels.

Code for text augmentation method leveraging large-scale language models