Baselight
Sign In

Global Hotspots Of Sharks And Longline Fishing

Machine-Learning-Assisted Spatial Distribution of At-Risk Species

@kaggle.thedevastator_global_hotspots_of_sharks_and_longline_fishing

Loading...
Loading...

About this Dataset

Global Hotspots Of Sharks And Longline Fishing

Global Hotspots of Sharks and Longline Fishing

Machine-Learning-Assisted Spatial Distribution of At-Risk Species

By [source]

About this dataset

This dataset provides a critical global assessment of hotspots for shark interactions with industrial longline fisheries. It utilizes machine-learning techniques to identify at-risk shark species and their spatial distribution patterns, highlighting crucial risk areas for threatened shark populations. Through the various parameters of the data, such as catch size, catch units, fish group and presence/absence of species among other details, this dataset can be used to better understand which fishing activities pose a potential threat to sharks while protecting those that are not detrimental. With this information we can help conserve our oceans' fragile ecosystems by maneuvering strategies towards sustainability in order to ensure healthy oceans for generations to come

More Datasets

For more datasets, click here.

Featured Notebooks

  • 🚨 Your notebook can be here! 🚨!

How to use the dataset

This dataset provides valuable insights into the spatial distribution of shark interactions with industrial longline fisheries. It can be used by researchers and conservationists to understand potential risk areas for endangered shark populations in different parts of the world, as well as for developing targeted strategies and measures to protect them.

In order to use this dataset effectively, it is important to understand its structure and content. This dataset contains columns that provide information on each observation including: .pred_class (predicted class of the observation), pres_abs (presence or absence of species), catch (catch data for the species), rfmo (Regional Fisheries Management Organization), year (year of the observation), latitude/longitude (location information) and a variety of other variables related to environmental values, sea surface temperature/height, chlorophyll-a concentration etc. The catch data has been transformed using various methods so that they are easier to use in develop predictive models.

In addition to these variables, this dataset also includes information on prices associated with each observed interaction as well as results from machine-learning-assisted models such as Random Forest Classification/Regression Trees, Minimum Node Size Classifier/Regressor and Mean Absolute Error scores resulting from the model. The results generated by these models can help identify potential hotspots for future interactions between sharks and industrial longline fishing operations which may lead us towards designing better policies for preserving threatened shark populations around the world

Research Ideas

  • This dataset can be used to predict future patterns of shark interactions with industrial longline fisheries, as well as identify hotspots of activity.
  • This dataset can provide valuable insight into how human activities and climate change may be impacting sharks and their environments.
  • This dataset can help provide early warnings for conservation efforts that should focus on particular areas in order to protect threatened species from unsustainable exploitation or other anthropogenic threats (e.g., habitat degradation)

Acknowledgements

If you use this dataset in your research, please credit the original authors.
Data Source

License

License: CC0 1.0 Universal (CC0 1.0) - Public Domain Dedication
No Copyright - You can copy, modify, distribute and perform the work, even for commercial purposes, all without asking permission. See Other Information.

Columns

File: IOTC_ll_untuned_final_predict.csv

Column name Description
.pred_class Predicted class of the species (String)
pres_abs Presence or absence of the species in the region (Boolean)
catch Total catch of the species (Integer)
rfmo Regional Fisheries Management Organization (String)
year Year of the data (Integer)
latitude Latitude of the location (Float)
longitude Longitude of the location (Float)
species_sciname Scientific name of the species (String)
catch_units Units of the catch (String)
gear_group Type of fishing gear used (String)
spatial_notes Notes about the spatial distribution of the species (String)
original_effort Original effort of the fishing gear (Integer)
species_commonname Common name of the species (String)
species_group Group of the species (String)
species_resolution Resolution of the species (String)
median_price_group Median price of the group (Float)
median_price_species Median price of the species (Float)
sdm Statistical distribution model (String)
zone Zone of the location (String)
location_cluster Cluster of the location (String)
mean_sst Mean sea surface temperature (Float)
median_sst Median sea surface temperature (Float)
min_sst Minimum sea surface temperature (Float)
max_sst Maximum sea surface temperature (Float)
sd_sst Standard deviation of sea surface temperature (Float)
se_sst Standard error of sea surface temperature (Float)
cv_sst Coefficient of variation of sea surface temperature (Float)
mean_chla Mean chlorophyll-a concentration (Float)
median_chla Median chlorophyll-a concentration (Float)
min_chla Minimum chlorophyll-a concentration (Float)
max_chla Maximum chlor
min_ssh Minimum sea surface height (Float)
max_ssh Maximum sea surface height (Float)
sd_ssh Standard deviation of sea surface height (Float)
se_ssh Standard error of sea surface height (Float)
cv_ssh Coefficient of variation of sea surface height (Float)
bycatch_total_effort_portugal_longline Total bycatch effort of Portugal longline (Integer)
bycatch_total_effort_spain_longline Total bycatch effort of Spain longline (Integer)
bycatch_total_effort_france_longline Total bycatch effort of France longline (Integer)
bycatch_total_effort_india_longline Total bycatch effort of India longline (Integer)
bycatch_total_effort_seychelles_longline Total bycatch effort of Seychelles longline (Integer)
bycatch_total_effort_taiwan_longline Total bycatch effort of Taiwan longline (Integer)
bycatch_total_effort_madagascar_longline Total bycatch effort of Madagascar longline (Integer)
bycatch_total_effort_mauritius_longline Total bycatch effort of Mauritius longline (Integer)
bycatch_total_effort_united_kingdom_longline Total bycatch effort of United Kingdom longline (Integer)
bycatch_total_effort_australia_longline Total bycatch effort of Australia longline (Integer)
bycatch_total_effort_mozambique_longline Total bycatch effort of Mozambique longline (Integer)
bycatch_total_effort_malaysia_longline Total bycatch effort of Malaysia longline (Integer)
bycatch_total_effort_indonesia_longline Total bycatch effort of Indonesia longline (Integer)
bycatch_total_effort_kenya_longline Total bycatch effort of Kenya longline (Integer)
.final_pred Predicted class of the species (String)
bycatch_total_effort Total bycatch effort (Integer)
bycatch_total_effort_china_longline Total bycatch effort of China longline (Integer)
bycatch_total_effort_korea_longline Total bycatch effort of Korea longline (Integer)
bycatch_total_effort_japan_longline Total bycatch effort of Japan longline (Integer)
sd_chla Standard deviation of chlorophyll-a concentration (Float)
se_chla Standard error of chlorophyll-a concentration (Float)
cv_chla Coefficient of variation of chlorophyll-a concentration (Float)
mean_ssh Mean sea surface height (Float)
median_ssh Median sea surface height (Float)

File: WCPFC_ll_models_others_results.csv

Column name Description
environmental_value The environmental value associated with the area. (Float)
include_ssh Whether or not sea surface height was included in the model. (Boolean)
price The price of the data. (Float)
catch_transformation The transformation applied to the catch data. (String)
mtry_class The maximum number of variables randomly sampled at each split in the classification tree. (Integer)
min_n_class The minimum observations in a node for a split to be considered valid. (Integer)
mtry_reg The maximum number of variables randomly sampled at each split in the regression tree. (Integer)
min_n_reg The minimum observations in a node for a split to be considered valid. (Integer)
rmse The root mean square error. (Float)
rsq The coefficient of determination. (Float)
mae The mean absolute error. (Float)

Acknowledgements

If you use this dataset in your research, please credit the original authors.
If you use this dataset in your research, please credit .

Tables

Iattc Ll Models Others Results

@kaggle.thedevastator_global_hotspots_of_sharks_and_longline_fishing.iattc_ll_models_others_results
  • 8.54 kB
  • 24 rows
  • 11 columns
Loading... 
CREATE TABLE iattc_ll_models_others_results (
  "environmental_value" VARCHAR,
  "include_ssh" BOOLEAN,
  "price" VARCHAR,
  "catch_transformation" VARCHAR,
  "mtry_class" BIGINT,
  "min_n_class" BIGINT,
  "mtry_reg" BIGINT,
  "min_n_reg" BIGINT,
  "rmse" DOUBLE,
  "rsq" DOUBLE,
  "mae" DOUBLE
);

Iattc Ll Untuned Final Predict

@kaggle.thedevastator_global_hotspots_of_sharks_and_longline_fishing.iattc_ll_untuned_final_predict
  • 14.8 MB
  • 339,300 rows
  • 54 columns
Loading... 
CREATE TABLE iattc_ll_untuned_final_predict (
  "n__pred_class" BIGINT  -- .pred Class,
  "pres_abs" VARCHAR,
  "catch" DOUBLE,
  "rfmo" VARCHAR,
  "year" BIGINT,
  "latitude" DOUBLE,
  "longitude" DOUBLE,
  "species_sciname" VARCHAR,
  "gear_group" VARCHAR,
  "spatial_notes" VARCHAR,
  "species_commonname" VARCHAR,
  "species_group" VARCHAR,
  "species_resolution" VARCHAR,
  "median_price_group" DOUBLE,
  "median_price_species" DOUBLE,
  "catch_units" VARCHAR,
  "original_effort" DOUBLE,
  "sdm" DOUBLE,
  "zone" VARCHAR,
  "location_cluster" BIGINT,
  "target_effort" DOUBLE,
  "target_effort_belize_longline" DOUBLE,
  "target_effort_china_longline" DOUBLE,
  "target_effort_french_polynesia_longline" DOUBLE,
  "target_effort_japan_longline" DOUBLE,
  "target_effort_korea_longline" DOUBLE,
  "target_effort_spain_longline" DOUBLE,
  "target_effort_taipei_longline" DOUBLE,
  "target_effort_united_states_of_america_longline" DOUBLE,
  "target_effort_vanuatu_longline" DOUBLE,
  "target_effort_panama_longline" DOUBLE,
  "mean_sst" DOUBLE,
  "median_sst" DOUBLE,
  "min_sst" DOUBLE,
  "max_sst" DOUBLE,
  "sd_sst" DOUBLE,
  "se_sst" DOUBLE,
  "cv_sst" DOUBLE,
  "mean_chla" DOUBLE,
  "median_chla" DOUBLE,
  "min_chla" DOUBLE,
  "max_chla" DOUBLE,
  "sd_chla" VARCHAR,
  "se_chla" VARCHAR,
  "cv_chla" VARCHAR,
  "mean_ssh" DOUBLE,
  "median_ssh" DOUBLE,
  "min_ssh" DOUBLE,
  "max_ssh" DOUBLE,
  "sd_ssh" DOUBLE,
  "se_ssh" DOUBLE,
  "cv_ssh" DOUBLE,
  "n__pred" DOUBLE  -- .pred,
  "n__final_pred" DOUBLE  -- .final Pred
);

Iccat Ll Models Others Results

@kaggle.thedevastator_global_hotspots_of_sharks_and_longline_fishing.iccat_ll_models_others_results
  • 8.54 kB
  • 24 rows
  • 11 columns
Loading... 
CREATE TABLE iccat_ll_models_others_results (
  "environmental_value" VARCHAR,
  "include_ssh" BOOLEAN,
  "price" VARCHAR,
  "catch_transformation" VARCHAR,
  "mtry_class" BIGINT,
  "min_n_class" BIGINT,
  "mtry_reg" BIGINT,
  "min_n_reg" BIGINT,
  "rmse" DOUBLE,
  "rsq" DOUBLE,
  "mae" DOUBLE
);

Iccat Ll Untuned Final Predict

@kaggle.thedevastator_global_hotspots_of_sharks_and_longline_fishing.iccat_ll_untuned_final_predict
  • 1.2 MB
  • 8,592 rows
  • 69 columns
Loading... 
CREATE TABLE iccat_ll_untuned_final_predict (
  "n__pred_class" BIGINT  -- .pred Class,
  "pres_abs" VARCHAR,
  "catch" DOUBLE,
  "rfmo" VARCHAR,
  "year" BIGINT,
  "latitude" BIGINT,
  "longitude" BIGINT,
  "species_sciname" VARCHAR,
  "catch_units" VARCHAR,
  "gear_group" VARCHAR,
  "spatial_notes" VARCHAR,
  "original_effort" BIGINT,
  "species_commonname" VARCHAR,
  "species_group" VARCHAR,
  "species_resolution" VARCHAR,
  "median_price_group" DOUBLE,
  "median_price_species" DOUBLE,
  "sdm" DOUBLE,
  "zone" VARCHAR,
  "location_cluster" BIGINT,
  "target_effort" DOUBLE,
  "target_effort_belize_longline" DOUBLE,
  "target_effort_china_longline" DOUBLE,
  "target_effort_japan_longline" DOUBLE,
  "target_effort_korea_longline" DOUBLE,
  "target_effort_spain_longline" DOUBLE,
  "target_effort_taipei_longline" DOUBLE,
  "target_effort_united_states_of_america_longline" DOUBLE,
  "target_effort_vanuatu_longline" DOUBLE,
  "mean_sst" DOUBLE,
  "median_sst" DOUBLE,
  "min_sst" DOUBLE,
  "max_sst" DOUBLE,
  "sd_sst" DOUBLE,
  "se_sst" DOUBLE,
  "cv_sst" DOUBLE,
  "mean_chla" DOUBLE,
  "median_chla" DOUBLE,
  "min_chla" DOUBLE,
  "max_chla" DOUBLE,
  "sd_chla" DOUBLE,
  "se_chla" DOUBLE,
  "cv_chla" DOUBLE,
  "mean_ssh" DOUBLE,
  "median_ssh" DOUBLE,
  "min_ssh" DOUBLE,
  "max_ssh" DOUBLE,
  "sd_ssh" DOUBLE,
  "se_ssh" DOUBLE,
  "cv_ssh" DOUBLE,
  "target_effort_barbados_longline" DOUBLE,
  "target_effort_bermuda_longline" DOUBLE,
  "target_effort_brazil_longline" DOUBLE,
  "target_effort_canada_longline" DOUBLE,
  "target_effort_malta_longline" DOUBLE,
  "target_effort_maroc_longline" DOUBLE,
  "target_effort_mexico_longline" DOUBLE,
  "target_effort_namibia_longline" DOUBLE,
  "target_effort_philippines_longline" DOUBLE,
  "target_effort_st_vincent_and_grenadines_longline" DOUBLE,
  "target_effort_trinidad_and_tobago_longline" DOUBLE,
  "target_effort_uruguay_longline" DOUBLE,
  "target_effort_venezuela_longline" DOUBLE,
  "target_effort_turks_and_caicos_longline" DOUBLE,
  "target_effort_great_britain_longline" DOUBLE,
  "target_effort_cote_d_ivoire_longline" DOUBLE,
  "target_effort_cyprus_longline" DOUBLE,
  "n__pred" DOUBLE  -- .pred,
  "n__final_pred" DOUBLE  -- .final Pred
);

Iotc Ll Models Others Results

@kaggle.thedevastator_global_hotspots_of_sharks_and_longline_fishing.iotc_ll_models_others_results
  • 8.54 kB
  • 24 rows
  • 11 columns
Loading... 
CREATE TABLE iotc_ll_models_others_results (
  "environmental_value" VARCHAR,
  "include_ssh" BOOLEAN,
  "price" VARCHAR,
  "catch_transformation" VARCHAR,
  "mtry_class" BIGINT,
  "min_n_class" BIGINT,
  "mtry_reg" BIGINT,
  "min_n_reg" BIGINT,
  "rmse" DOUBLE,
  "rsq" DOUBLE,
  "mae" DOUBLE
);

Iotc Ll Untuned Final Predict

@kaggle.thedevastator_global_hotspots_of_sharks_and_longline_fishing.iotc_ll_untuned_final_predict
  • 772.49 kB
  • 13,500 rows
  • 61 columns
Loading... 
CREATE TABLE iotc_ll_untuned_final_predict (
  "n__pred_class" BIGINT  -- .pred Class,
  "pres_abs" VARCHAR,
  "catch" DOUBLE,
  "rfmo" VARCHAR,
  "year" BIGINT,
  "latitude" DOUBLE,
  "longitude" BIGINT,
  "species_sciname" VARCHAR,
  "catch_units" VARCHAR,
  "gear_group" VARCHAR,
  "spatial_notes" VARCHAR,
  "original_effort" BIGINT,
  "species_commonname" VARCHAR,
  "species_group" VARCHAR,
  "species_resolution" VARCHAR,
  "median_price_group" DOUBLE,
  "median_price_species" DOUBLE,
  "sdm" DOUBLE,
  "zone" VARCHAR,
  "location_cluster" BIGINT,
  "bycatch_total_effort" DOUBLE,
  "bycatch_total_effort_china_longline" DOUBLE,
  "bycatch_total_effort_korea_longline" DOUBLE,
  "bycatch_total_effort_japan_longline" DOUBLE,
  "mean_sst" DOUBLE,
  "median_sst" DOUBLE,
  "min_sst" DOUBLE,
  "max_sst" DOUBLE,
  "sd_sst" DOUBLE,
  "se_sst" DOUBLE,
  "cv_sst" DOUBLE,
  "mean_chla" DOUBLE,
  "median_chla" DOUBLE,
  "min_chla" DOUBLE,
  "max_chla" DOUBLE,
  "sd_chla" DOUBLE,
  "se_chla" DOUBLE,
  "cv_chla" DOUBLE,
  "mean_ssh" DOUBLE,
  "median_ssh" DOUBLE,
  "min_ssh" DOUBLE,
  "max_ssh" DOUBLE,
  "sd_ssh" DOUBLE,
  "se_ssh" DOUBLE,
  "cv_ssh" DOUBLE,
  "bycatch_total_effort_portugal_longline" DOUBLE,
  "bycatch_total_effort_spain_longline" DOUBLE,
  "bycatch_total_effort_france_longline" DOUBLE,
  "bycatch_total_effort_india_longline" DOUBLE,
  "bycatch_total_effort_seychelles_longline" DOUBLE,
  "bycatch_total_effort_taiwan_longline" DOUBLE,
  "bycatch_total_effort_madagascar_longline" DOUBLE,
  "bycatch_total_effort_mauritius_longline" DOUBLE,
  "bycatch_total_effort_united_kingdom_longline" DOUBLE,
  "bycatch_total_effort_australia_longline" DOUBLE,
  "bycatch_total_effort_mozambique_longline" DOUBLE,
  "bycatch_total_effort_malaysia_longline" DOUBLE,
  "bycatch_total_effort_indonesia_longline" DOUBLE,
  "bycatch_total_effort_kenya_longline" DOUBLE,
  "n__pred" DOUBLE  -- .pred,
  "n__final_pred" DOUBLE  -- .final Pred
);

N 1x1 Count All Rfmos Ll Effort Results

@kaggle.thedevastator_global_hotspots_of_sharks_and_longline_fishing.n_1x1_count_all_rfmos_ll_effort_results
  • 4.97 kB
  • 12 rows
  • 6 columns
Loading... 
CREATE TABLE n_1x1_count_all_rfmos_ll_effort_results (
  "model" VARCHAR,
  "effort_source" VARCHAR,
  "rfmo" VARCHAR,
  "rmse" DOUBLE,
  "rsq" DOUBLE,
  "mae" DOUBLE
);

N 1x1 Mt To Count All Rfmos Ll Effort Results

@kaggle.thedevastator_global_hotspots_of_sharks_and_longline_fishing.n_1x1_mt_to_count_all_rfmos_ll_effort_results
  • 4.89 kB
  • 9 rows
  • 6 columns
Loading... 
CREATE TABLE n_1x1_mt_to_count_all_rfmos_ll_effort_results (
  "model" VARCHAR,
  "effort_source" VARCHAR,
  "rfmo" VARCHAR,
  "rmse" DOUBLE,
  "rsq" DOUBLE,
  "mae" DOUBLE
);

N 5x5 Count All Rfmos Ll Effort Results

@kaggle.thedevastator_global_hotspots_of_sharks_and_longline_fishing.n_5x5_count_all_rfmos_ll_effort_results
  • 4.97 kB
  • 12 rows
  • 6 columns
Loading... 
CREATE TABLE n_5x5_count_all_rfmos_ll_effort_results (
  "model" VARCHAR,
  "effort_source" VARCHAR,
  "rfmo" VARCHAR,
  "rmse" DOUBLE,
  "rsq" DOUBLE,
  "mae" DOUBLE
);

N 5x5 Mt To Count All Rfmos Ll Effort Results

@kaggle.thedevastator_global_hotspots_of_sharks_and_longline_fishing.n_5x5_mt_to_count_all_rfmos_ll_effort_results
  • 4.89 kB
  • 9 rows
  • 6 columns
Loading... 
CREATE TABLE n_5x5_mt_to_count_all_rfmos_ll_effort_results (
  "model" VARCHAR,
  "effort_source" VARCHAR,
  "rfmo" VARCHAR,
  "rmse" DOUBLE,
  "rsq" DOUBLE,
  "mae" DOUBLE
);

Wcpfc Ll Models Others Results

@kaggle.thedevastator_global_hotspots_of_sharks_and_longline_fishing.wcpfc_ll_models_others_results
  • 8.56 kB
  • 24 rows
  • 11 columns
Loading... 
CREATE TABLE wcpfc_ll_models_others_results (
  "environmental_value" VARCHAR,
  "include_ssh" BOOLEAN,
  "price" VARCHAR,
  "catch_transformation" VARCHAR,
  "mtry_class" BIGINT,
  "min_n_class" BIGINT,
  "mtry_reg" BIGINT,
  "min_n_reg" BIGINT,
  "rmse" DOUBLE,
  "rsq" DOUBLE,
  "mae" DOUBLE
);

Wcpfc Ll Untuned Final Predict

@kaggle.thedevastator_global_hotspots_of_sharks_and_longline_fishing.wcpfc_ll_untuned_final_predict
  • 781.04 kB
  • 25,857 rows
  • 45 columns
Loading... 
CREATE TABLE wcpfc_ll_untuned_final_predict (
  "n__pred_class" BIGINT  -- .pred Class,
  "pres_abs" VARCHAR,
  "catch" BIGINT,
  "rfmo" VARCHAR,
  "year" BIGINT,
  "latitude" DOUBLE,
  "longitude" DOUBLE,
  "species_sciname" VARCHAR,
  "catch_units" VARCHAR,
  "gear_group" VARCHAR,
  "spatial_notes" VARCHAR,
  "original_effort" BIGINT,
  "species_commonname" VARCHAR,
  "species_group" VARCHAR,
  "species_resolution" VARCHAR,
  "median_price_group" DOUBLE,
  "median_price_species" DOUBLE,
  "sdm" DOUBLE,
  "zone" VARCHAR,
  "location_cluster" BIGINT,
  "bycatch_total_effort" DOUBLE,
  "mean_sst" DOUBLE,
  "median_sst" DOUBLE,
  "min_sst" DOUBLE,
  "max_sst" DOUBLE,
  "sd_sst" DOUBLE,
  "se_sst" DOUBLE,
  "cv_sst" DOUBLE,
  "mean_chla" DOUBLE,
  "median_chla" DOUBLE,
  "min_chla" DOUBLE,
  "max_chla" DOUBLE,
  "sd_chla" DOUBLE,
  "se_chla" DOUBLE,
  "cv_chla" DOUBLE,
  "mean_ssh" DOUBLE,
  "median_ssh" DOUBLE,
  "min_ssh" DOUBLE,
  "max_ssh" DOUBLE,
  "sd_ssh" DOUBLE,
  "se_ssh" DOUBLE,
  "cv_ssh" DOUBLE,
  "bycatch_total_effort_na_longline" DOUBLE,
  "n__pred" DOUBLE  -- .pred,
  "n__final_pred" DOUBLE  -- .final Pred
);

Share link

Anyone who has the link will be able to view this.