Skip to content

Frequently Asked Questions (FAQs)

Common questions and answers about the Darukaa.Earth platform.

General

What is Darukaa.Earth?

Darukaa.Earth is a cloud-native biodiversity and climate-risk platform for monitoring, analysis, carbon & biodiversity credit calculation, and stakeholder workflows. It combines remote sensing, in-situ sensors (acoustic & camera), and AI/ML models.

Who should use the platform?

Project developers, conservation/NGO teams, verifiers, researchers, and enterprises doing nature-based projects: carbon, biodiversity, restoration, or climate risk assessment.

What makes Darukaa.Earth different?

  • Multimodal Data Integration - Combines satellite, IoT, and field data
  • AI/ML Powered - Advanced models for species detection and analysis
  • Compliance Ready - Supports TNFD, CSRD, BRSR reporting standards
  • End-to-End Solution - From data collection to credit issuance

Accounts & Authentication

How do I create an account?

Sign up via the web UI (app.darukaa.com) or use the API endpoint POST /api/v1/auth/signup. Verify your email to complete registration.

How do I authenticate with the API?

Obtain an access token by calling POST /auth/login with email/password. Send Authorization: Bearer <access_token> in API requests.

How long are tokens valid and how do I refresh them?

Access tokens are short-lived; use POST /auth/refresh with your refresh token to get a new access token. Token lifetimes are configured on the server.

What should my client do on 401 responses?

Attempt token refresh using the refresh token. If refresh fails, prompt user to login again. Capture request_id from the error for support.

API & Integration

What is the base API URL and versioning policy?

Use https://api.darukaa.com. Breaking changes will be released under new /vX versions. Subscribe to changelog for updates.

How do I paginate list responses?

Use the skip/limit query params. Expect list responses to include pagination metadata: total, limit, skip.

What are common HTTP status codes and error formats?

Standard codes: 200/201 (success), 400 (bad input), 401 (unauthorized), 403 (forbidden), 404 (not found), 413 (payload too large), 429 (rate limited), 500 (server error).

Error body includes code, message, details, request_id, timestamp:

{
  "error": {
    "code": "INVALID_PROJECT_ID",
    "message": "Project not found",
    "details": "Ensure project id is valid and accessible",
    "request_id": "req_abc123",
    "timestamp": "2025-12-04T13:30:00Z"
  }
}

Data & Uploads

What formats are supported for geodata and media?

  • Vectors: GeoJSON (RFC 7946), shapefile zip
  • Rasters: GeoTIFF
  • Audio: WAV (16-bit, ≥44.1 kHz preferred), MP3, M4A, WEBM
  • Images: JPEG/PNG with EXIF

What are file size and upload limits?

  • Single upload max: 500 MB for general uploads
  • Audio upload: 25 MB per file, max 20 files per request, 300 seconds max duration
  • Client should handle 413 responses appropriately

Can I bulk-upload sites or sensor deployments?

Yes — bulk CSV uploads are supported. Use the provided sample CSV template. Ensure coordinates are WGS84 (EPSG:4326) unless otherwise specified.

How soon after upload will data be processed?

Processing time depends on file size and queue load: - Small audio/images: typically processed within minutes - Large satellite jobs: may take longer - All processing responses include processing_status and processing_message

Bioacoustics, Camera & Inference

How do I upload audio for inference?

Upload via POST /api/v1/deployments/{deployment_id}/audio/upload (multipart or base64 depending on API). After upload, inference may run automatically or call POST /api/v1/admin/inference/file/{file_id} to trigger inference.

What models and species coverage exist?

The platform supports acoustic and image models; the model version and metadata are returned with inference. Coverage varies by deployment. Validate high-priority detections via manual review workflow.

What outputs come from inference?

Predictions array, model metadata (model_version_id), acoustic indices (ACI, ADI, BI, NDSI), spectrogram URL, and an inference_id. Use these for dashboards or downstream analysis.

How are uncertain predictions handled?

Predictions include confidence scores. Platform enforces a configurable reporting threshold (default recommended: 0.7). Low-confidence detections route to manual verification queues.

Troubleshooting & Common Errors

I received 429 Too Many Requests — what now?

Back off and retry after Retry-After header. Implement exponential backoff and respect rate-limit headers (X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset).

My file upload returns 413 Payload Too Large — what should I do?

Split the upload into smaller chunks if supported, compress/convert files, or use the platform's batch upload API with signed URLs. Contact support if you need higher limits.

I can't find a project or site — 404 — what to check?

Verify you're using the correct project_id/site_id, that the account has access, and that the get_satellite_images flag (if used) is correct. Provide request_id and a timestamp when contacting support.

Inference returned empty predictions — why?

Possible reasons: no detectable events in audio, low SNR, unsupported species, or model version limitations. Check acoustic_indices and spectrograms for signal, and rerun with a longer clip or higher sample rate.

Support

For additional support: - Email: info@Darukaa.com - Website: https://www.darukaa.earth - Documentation: https://docs.darukaa.com - API Base URL: https://api.darukaa.com