---
language: en
license: apache-2.0
datasets:
- ESGBERT/WaterForestBiodiversityNature_2200
tags:
- ESG
- environmental
- forest
---

# Model Card for EnvironmentalBERT-water

## Model Description

Based on [this paper](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4665715), this is the EnvironmentalBERT-forest language model. A language model that is trained to better classify forest texts in the ESG/nature domain.

Using the [EnvironmentalBERT-base](https://huggingface.co/ESGBERT/EnvironmentalBERT-base) model as a starting point, the EnvironmentalBERT-forest Language Model is additionally fine-trained on a 2.2k forest dataset to detect forest text samples.

## How to Get Started With the Model

See these tutorials on Medium for a guide on [model usage](https://medium.com/@schimanski.tobi/analyzing-esg-with-ai-and-nlp-tutorial-1-report-analysis-towards-esg-risks-and-opportunities-8daa2695f6c5?source=friends_link&sk=423e30ac2f50ee4695d258c2c4d54aa5), [large-scale analysis](https://medium.com/@schimanski.tobi/analyzing-esg-with-ai-and-nlp-tutorial-2-large-scale-analyses-of-environmental-actions-0735cc8dc9c2?source=friends_link&sk=13a5aa1999fbb11e9eed4a0c26c40efa), and [fine-tuning](https://medium.com/@schimanski.tobi/analyzing-esg-with-ai-and-nlp-tutorial-3-fine-tune-your-own-models-e3692fc0b3c0?source=friends_link&sk=49dc9f00768e43242fc1a76aa0969c70).

It is highly recommended to first classify a sentence to be "environmental" or not with the [EnvironmentalBERT-environmental](https://huggingface.co/ESGBERT/EnvironmentalBERT-environmental) model before classifying whether it is "forest" or not.

You can use the model with a pipeline for text classification:

```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
 
tokenizer_name = "ESGBERT/EnvironmentalBERT-forest"
model_name = "ESGBERT/EnvironmentalBERT-forest"
 
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(tokenizer_name, max_len=512)
 
pipe = pipeline("text-classification", model=model, tokenizer=tokenizer) # set device=0 to use GPU
 
# See https://huggingface.co/docs/transformers/main_classes/pipelines#transformers.pipeline
print(pipe("A large portion of trees in the Amazonas is dying each year.", padding=True, truncation=True))
```

## More details can be found in the paper

```bibtex
@article{Schimanski23ExploringNature,
    title={{Exploring Nature: Datasets and Models for Analyzing Nature-Related Disclosures}},
    author={Tobias Schimanski and Chiara Colesanti Senni and Glen Gostlow and Jingwei Ni and Tingyu Yu and Markus Leippold},
    year={2023},
    journal={Available on SSRN: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4665715},
}
```