Dataset DOI: 10.5061/dryad.v6wwpzh7h

Description of the data and file structure

Background

The main goal of the study was to develop a practical, low-cost yield monitoring system for manually harvested strawberries to encourage widespread adoption. A key design decision was to use an affordable GPS relying on the freely available Satellite Based Augmentation System (SBAS) corrections. Pickers were not trained prior to using the iCarritos, and the system was deployed in a commercial field with minimal disruption to established harvesting practices. Data were collected as part of the USDA Agricultural Research Service (USDA-ARS) Areawide Pest Management Grant Program project, “Site-Specific Soil Pest Management in Strawberry and Vegetable Cropping Systems Using Crop Rotation and a Needs-Based Variable Rate Fumigation Strategy,” through Non-Assistance Cooperative Agreements.

Value of the Data

• This is a comprehensive dataset for developing and validating precision yield estimation and mapping techniques for manually harvested crops, especially strawberries. 

• The dataset enables the data-driven analysis of spatial and temporal yield variability in strawberry fields, which can inform decision-making in field management, including nutrient application, irrigation, and pest control. 

• Researchers in precision agriculture can reuse this data to develop new algorithms for worker activity recognition, efficiency estimation, yield forecasting, and crop management strategies. 

• Agricultural engineers and data scientists can utilize this dataset to improve existing data processing pipelines or develop new ones for handling sensor data from manual harvesting operations. 
• The data is gathered from scalable, practical, and low-cost picking carts, which could provide practical solutions for yield estimation and mapping for manually harvested crops, potentially benefiting both researchers and industry practitioners. 

Files and variables

File: datasets.zip

Description: The publicly released dataset consists of three main folders: BedCenters, SantaMaria, and Salinas. The BedCenters folder contains two files, Salinas2024.txt and SantaMaria2024.txt, each providing the coordinates of the bed center endpoints. The SantaMaria and Salinas folders contain harvest data from all carts collected throughout the harvest season. The following section provides a detailed description of each component.

1. SantaMaria, Salinas folders:
   These folders contain complete season-long harvest data from all iCarritos, along with harvested tray records. The subfolders are organised by date (e.g., DD-MM-YY/) and contain raw harvest files (cart1.csv, cart2.csv, …, cartN.csv) corresponding to individual carts. Each CSV file contains following columns:

   • GPS_TOW: GPS Time of Week (milliseconds).
   • LAT, LON, HEIGHT: Geographic coordinates (degrees and metres).
   • ax, ay, az: Acceleration along the x, y, and z axes (m s⁻²).
   • raw_mass: Raw harvest mass (kg).

   The accompanying Excel file, harvested_trays.xlsx, records the number of trays harvested per iCarrito for each harvest day, with the following columns:

   • cart_id: iCarrito identifier.
   • no_trays: Number of trays harvested by that iCarrito.

Dataset directory structure

datasets/
├── BedCenters/
│   ├── Salinas2024.txt
│   └── SantaMaria2024.txt
├── SantaMaria/
│   ├── DD-MM-YY/
│   │   ├── cart1.csv
│   │   ├── cart2.csv
│   │   ├── ...
│   │   └── cartN.csv
│   └── harvested_trays.xlsx
└── Salinas/
    ├── DD-MM-YY/
    │   ├── cart1.csv
    │   ├── cart2.csv
    │   ├── ...
    │   └── cartN.csv
    └── harvested_trays.xlsx

Code/software

https://github.com/uddhavbhattarai/iCarritoYieldEstimationandMapping.git

Human subjects data

While this dataset was derived from field operations involving human workers, it does not contain any personally identifiable information (PII). The dataset consists solely of sensor data collected from instrumented strawberry-picking carts (iCarritos), including GPS coordinates, timestamps, IMU measurements, and load-cell readings. No personal attributes, names, worker identifiers, or demographic information were collected. Carts were used interchangeably by multiple pickers during commercial harvesting operations, and no individual was permanently or uniquely associated with any specific cart. As a result, there is no linkage between the recorded data and any identifiable person.