HERSS-MAIZE 2025; High-rEsolution dRone dataset for Site-Specific weed wanagement in Maize (San Piero - Pisa, Tuscany, Italy) (DOI 10.82522/bs5d-wy47)
Weed management (WM) is recognised as one of the major challenges in modern agriculture, particularly within the framework of the Farm to Fork strategy, which aims to reduce pesticide use by 50% by 2030 while maintaining high crop productivity. Precision agriculture techniques, and especially Site-Specific Weed Management (SSWM), have emerged as promising approaches to achieve these goals by optimising post-emergence herbicide application according to the spatial distribution of weeds. The SSWM process is characterised by three fundamental phases: weed detection (WD), potential damage (PD) estimation, and precision herbicide application (PHA), all supported by advanced sensing, imaging, and artificial intelligence (AI) methods.
The first HERSS-MAIZE dataset was acquired in 2024 over a maize experimental field measuring approximately 0.8 ha, located in San Piero (Pisa, Tuscany, Italy), during the crop’s critical period of susceptibility to weed competition. To ensure temporal continuity and enable multi-year analyses of weed dynamics and crop–weed interactions, a subsequent acquisition was conducted in 2025 over the same experimental site, following a comparable acquisition protocol.
In total, thirteen UAV surveys were conducted using two different drone platforms—DJI MINI 3 PRO and DJI Mavic 3M—to compare data quality and assess the feasibility of SSWM under varying technological conditions. All acquired images were ortho-rectified to produce 13 high-resolution orthomosaics, representing temporal variations in vegetation cover and weed development. The dataset also incorporates flight metadata, sensor characteristics, and georeferencing information, thereby facilitating integration into Geographic Information System (GIS) environments or utilisation in machine learning and deep learning workflows for weed detection and crop monitoring.
The primary objective of the HERSS-MAIZE dataset is to provide a high-resolution, multi-temporal UAV-based resource for developing, validating, and benchmarking algorithms and methodologies for Weed Detection and Site-Specific Weed Management in maize. The incorporation of data from both professional and consumer-grade UAVs within the dataset facilitates research into scalable, cost-effective precision agriculture solutions aimed at reducing herbicide use and enhancing environmental sustainability. Ultimately, HERSS-MAIZE supports advancements in AI-driven weed mapping, adaptive management zone delineation, and precision spraying strategies aligned with sustainable agricultural practices.
Simple
Identification info
-
Date (Creation)
- 2025-05-30
-
Date (Publication)
- 2025-10-15
-
Purpose
-
The HERSS-MAIZE dataset was developed to support the development and evaluation of algorithms for weed detection and site-specific weed management (SSWM) in maize. Its primary goal is to provide a high-resolution, multi-temporal UAV-based benchmark that enables the study and advancement of SSWM techniques using real-world field data. By incorporating imagery from both professional and consumer-grade UAVs, the dataset offers a versatile resource for testing remote sensing, computer vision, and machine learning approaches under different technological conditions. Ultimately, HERSS-MAIZE aims to foster research in precision agriculture practices that improve input efficiency and promote sustainable weed control strategies.
-
Status
-
Completed
- Point of contact
-
Role Organisation Electronic mail address Point of contactCNR Istituto di Geoscienze e Georisorse
AuthorCNR Istituto di Geoscienze e Georisorse
AuthorUNIPI Dipartimento di Scienze Agrarie, Alimentari e Agro-ambientali (DiSAAA-a)
Principal investigatorUNIPI Dipartimento di Scienze Agrarie, Alimentari e Agro-ambientali (DiSAAA-a)
CollaboratorUNIPI Dipartimento di Scienze Agrarie, Alimentari e Agro-ambientali (DiSAAA-a)
CollaboratorCNR Istituto di Scienze e Tecnologie dell'Informazione
CollaboratorCNR Istituto di Scienze e Tecnologie dell'Informazione
Resource providerCNR Istituto di Geoscienze e Georisorse
ContributorCNR Istituto di Informatica e Telematica
-
Spatial representation type
Spatial resolution
Equivalent scale
-
Denominator
- 1
-
Topic category
-
-
Environment
-
Geoscientific information
-
Imagery base maps earth cover
-
Farming
-
Extent
Temporal extent
-
Time period
- 2025-05-30 2025-07-01
Extent
))
Extent
Vertical element
-
Minimum value
- 1
-
Maximum value
- 1
-
Maintenance and update frequency
-
As needed
-
Product
-
-
UAS, RGB, Precision Agriculture, SSWM, Weeds, Maize
-
-
Place
-
-
SanPiero a Grado, Pisa, Tuscany, Italy
-
- EU Legislation
Resource constraints
-
Use limitation
-
This dataset is currently restricted and subject to an embargo. Public access and download will be granted starting from November 2027
-
Access constraints
-
Restricted
-
Use constraints
-
Restricted
-
Language
- English
-
Character encoding
-
UTF8
Distribution Information
-
OnLine resource
-
Mappa della risorsa
Distribution Information
- Distributor contact
-
Role Organisation Electronic mail address DistributorCNR Istituto di Geoscienze e Georisorse
Resource lineage
-
Statement
-
The RGB datasets were acquired to monitor the temporal evolution of weed infestation and crop growth within a maize field. The data were collected with the objective of supporting the development and validation of weed detection and site-specific weed management (SSWM) techniques. This enabled the identification of weed patches and crop–weed competition dynamics throughout the growing season
-
Hierarchy level
-
Dataset
Reference System Information
-
Reference system identifier
- EPSG:4326 - WGS 1984
Metadata
-
Metadata identifier
- urn:uuid/2ee5af30-a569-4ddb-8206-b6dd478fd00f
-
Language
- English
-
Character encoding
-
anyValidURI
- Contact
-
Role Organisation Electronic mail address Point of contactCNR Istituto di Geoscienze e Georisorse
Type of resource
-
Resource type
-
Dataset
-
Metadata linkage
-
https://metadati.remote.adrpi.cnr.it/srv/api/records/2ee5af30-a569-4ddb-8206-b6dd478fd00f
-
Date info (Creation)
- 2025-10-28T14:46:56.101656Z
-
Date info (Creation)
- 2025-10-08T13:20:06.203197Z
-
Date info (Creation)
- 2025-10-03T07:49:48.790713Z
-
Date info (Revision)
- 2025-12-04T11:11:45.501815Z
-
Date info (Creation)
- 2005-03-31T19:13:30
Metadata standard
-
Title
-
ISO 19115-3
)))
