Agent SkillsAgent Skills
benchflow-ai

usgs-data-download

@benchflow-ai/usgs-data-download
benchflow-ai
1,376
318 forks
Updated 6/20/2026
View on GitHub

Download water level data from USGS using the dataretrieval package. Use when accessing real-time or historical streamflow data, downloading gage height or discharge measurements, or working with USGS station IDs.

Installation

$npx agent-skills-cli install @benchflow-ai/usgs-data-download
Claude Code
Cursor
Copilot
Codex
Antigravity

Details

Pathtasks/flood-risk-analysis/environment/skills/usgs-data-download/SKILL.md
Branchmain
Scoped Name@benchflow-ai/usgs-data-download

Usage

After installing, this skill will be available to your AI coding assistant.

Verify installation:

npx agent-skills-cli list

Skill Instructions


name: usgs-data-download description: Download water level data from USGS using the dataretrieval package. Use when accessing real-time or historical streamflow data, downloading gage height or discharge measurements, or working with USGS station IDs. license: MIT

USGS Data Download Guide

Overview

This guide covers downloading water level data from USGS using the dataretrieval Python package. USGS maintains thousands of stream gages across the United States that record water levels at 15-minute intervals.

Installation

pip install dataretrieval

nwis Module (Recommended)

The NWIS module is reliable and straightforward for accessing gage height data.

from dataretrieval import nwis

# Get instantaneous values (15-min intervals)
df, meta = nwis.get_iv(
    sites='<station_id>',
    start='<start_date>',
    end='<end_date>',
    parameterCd='00065'
)

# Get daily values
df, meta = nwis.get_dv(
    sites='<station_id>',
    start='<start_date>',
    end='<end_date>',
    parameterCd='00060'
)

# Get site information
info, meta = nwis.get_info(sites='<station_id>')

Parameter Codes

CodeParameterUnitDescription
00065Gage heightfeetWater level above datum
00060DischargecfsStreamflow volume

nwis Module Functions

FunctionDescriptionData Frequency
nwis.get_iv()Instantaneous values~15 minutes
nwis.get_dv()Daily valuesDaily
nwis.get_info()Site informationN/A
nwis.get_stats()Statistical summariesN/A
nwis.get_peaks()Annual peak dischargeAnnual

Returned DataFrame Structure

The DataFrame has a datetime index and these columns:

ColumnDescription
site_noStation ID
00065Water level value
00065_cdQuality code (can ignore)

Downloading Multiple Stations

from dataretrieval import nwis

station_ids = ['<id_1>', '<id_2>', '<id_3>']
all_data = {}

for site_id in station_ids:
    try:
        df, meta = nwis.get_iv(
            sites=site_id,
            start='<start_date>',
            end='<end_date>',
            parameterCd='00065'
        )
        if len(df) > 0:
            all_data[site_id] = df
    except Exception as e:
        print(f"Failed to download {site_id}: {e}")

print(f"Successfully downloaded: {len(all_data)} stations")

Extracting the Value Column

# Find the gage height column (excludes quality code column)
gage_col = [c for c in df.columns if '00065' in str(c) and '_cd' not in str(c)]

if gage_col:
    water_levels = df[gage_col[0]]
    print(water_levels.head())

Common Issues

IssueCauseSolution
Empty DataFrameStation has no data for date rangeTry different dates or use get_iv()
get_dv() returns emptyNo daily gage height dataUse get_iv() and aggregate
Connection errorNetwork issueWrap in try/except, retry
Rate limitedToo many requestsAdd delays between requests

Best Practices

  • Always wrap API calls in try/except for failed downloads
  • Check len(df) > 0 before processing
  • Station IDs are 8-digit strings with leading zeros (e.g., '04119000')
  • Use get_iv() for gage height, as daily data is often unavailable
  • Filter columns to exclude quality code columns (_cd)
  • Break up large requests into smaller time periods to avoid timeouts