season

Problem Statement

👉 Download the case studies here

A large-scale agricultural enterprise struggled with monitoring crop health across vast farmlands. Traditional methods were labor-intensive and prone to delays in detecting diseases or resource deficiencies, leading to reduced yields and higher operational costs. The enterprise needed an advanced solution to monitor crop health, optimize farming practices, and enhance productivity.

Challenge

Implementing a smart agriculture system presented the following challenges:

Capturing and processing data from vast and diverse farmland efficiently.

Detecting early signs of crop diseases and nutrient deficiencies to prevent widespread damage.

Optimizing the use of resources such as water, fertilizers, and pesticides to reduce costs and environmental impact.

Solution Provided

A comprehensive smart agriculture and crop monitoring system was developed using drones equipped with computer vision, IoT sensors, and AI analytics. The solution was designed to:

Provide aerial imagery of crops to identify health patterns and detect diseases or pests.

Monitor soil and weather conditions in real-time through IoT sensors.

Deliver actionable insights for precise resource allocation and farming decisions.

Development Steps

Data Collection

Deployed drones to capture high-resolution images of crops across the farmland. Installed IoT sensors to monitor soil moisture, temperature, humidity, and nutrient levels.

Preprocessing

Processed drone imagery to enhance features such as color, texture, and shape for accurate analysis. Standardized data from IoT sensors to ensure compatibility and reliability.

Model Training

Developed computer vision models to detect crop diseases, pest infestations, and growth anomalies. Built predictive analytics models to forecast optimal planting, irrigation, and harvesting times.

Validation

Tested the system on pilot farmlands to ensure accurate disease detection, resource optimization, and yield prediction.

Deployment

Implemented the solution across the enterprise’s farmland, integrating it with existing farm management systems for seamless operation.

Continuous Monitoring & Improvement

Established a feedback loop to refine models based on new data, improving detection accuracy and predictive capabilities.

Results

Increased Crop Yields

The system improved crop health and productivity, resulting in a 20% increase in overall yields.

Optimized Resource Usage

Precise monitoring and insights reduced water, fertilizer, and pesticide usage, lowering costs and environmental impact.

Early Detection of Crop Diseases

AI-driven disease detection enabled timely interventions, preventing widespread crop loss.

Enhanced Decision-Making

Farmers benefited from data-driven insights, allowing them to make informed decisions about planting, irrigation, and harvesting.

Scalable and Sustainable Solution

The system demonstrated scalability, adapting to various crop types and farm sizes, while supporting sustainable farming practices.

pH

Smart Farming

## Overview

Smart Farming is a dataset for object detection tasks - it contains Rice annotations for 964 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [MIT license](https://creativecommons.org/licenses/MIT).

The Cauliflower Leaf Disease Dataset is a curated collection of high-quality images designed for machine learning and deep learning applications in plant disease detection. The dataset comprises 2,661 images categorized into three classes: Healthy (934), Insect Hole (639), and Black Rot (1,088). The images are collected under varying lighting conditions and angles to enhance model generalization.

Key Features: Healthy Leaves (934): Images of fresh, disease-free cauliflower leaves. Insect Hole (639): Leaves showing visible insect damage, such as holes caused by pests. Black Rot (1,088): Leaves affected by Xanthomonas campestris pv. campestris, a bacterial infection causing blackened veins and necrotic lesions.

Applications: Computer Vision: Image segmentation, feature extraction, and object detection for plant pathology studies. Machine Learning: Traditional classifiers (SVM, Random Forest) and feature engineering techniques for automated classification. Deep Learning: Convolutional Neural Networks (CNNs), Transfer Learning (ResNet, VGG, EfficientNet), and Explainable AI (Grad-CAM) to identify disease patterns. Agricultural Decision Support: Real-time disease monitoring, precision farming applications, and smartphone-based diagnosis for farmers.

This dataset is a crucial resource for researchers working on AI-driven plant disease identification and can contribute to the advancement of precision agriculture and sustainable farming solutions.

1. Introduction

This cherry tree disease detection dataset is a multimodal, multi-angle dataset which was constructed for monitoring the growth of cherry trees, including stress analysis and prediction. An orchard of cherry trees is considered in the area of Western Macedonia, where 577 cherry trees were recorded in a full crop season starting from Jul. 2021 to Jul. 2022. The dataset includes a) aerial / Unmanned Aerial Vehicle (UAV) images, b) ground RGB images/photos, and c) ground multispectral images/photos. Two agronomist experts annotated the dataset by identifying a stress, which in this case is a common disease in cherry trees known as Armillaria [1][2].

2. Citation

Please cite the following papers when using this dataset:

C. Chaschatzis, C. Karaiskou, E. Mouratidis, E. Karagiannis, and P. Sarigiannidis, “Detection and Characterization of Stressed Sweet Cherry Tissues Using Machine Learning”, Drones, vol. 6, no. 1, 2022.

P. Radoglou-Grammatikis, P. Sarigiannidis, T. Lagkas, & I. Moscholios, “A compilation of UAV applications for precision agriculture,” Computer Networks, vol. 172, no. 107148, 2020.

A. Lytos, T. Lagkas, P. Sarigiannidis, M. Zervakis, & G. Livanos, “Towards smart farming: Systems, frameworks and exploitation of multiple sources,” Computer Networks, vol. 172, no. 107147, 2020.

3. Cherry tree mapping

In this dataset, an orchard of cherry trees is considered in the area of Western Macedonia, where 577 cherry trees were recorded in a full crop season starting from Jul. 2021 to Jul. 2022. The tree mapping within the orchard is depicted in Fig. 1. (please refer to the ReadMe file), where each circle represents a cherry tree. Labels on the circles (green, red etc) will be elaborated in the following Sections. The five time periods, where the orchard was recorded are: 8th of Jul. 2021, 16th of Sep. 2021, 3rd of Nov. 2021, 26th of May 2022, and 13th of Jul. 2022, providing data to a full year of life cycle.

4. Dataset Modalities

The dataset includes a) aerial / Unmanned Aerial Vehicle (UAV) images, b) ground RGB images/photos, and c) ground multispectral images/photos. Two agronomist experts annotated the dataset by identifying a stress, which in this case is a common disease in cherry trees known as Armillaria [1][2]. In particular, the following modalities are featured in the dataset:

Ground RGB images

Ground multispectral images

UAV/Aerial images (RGB, multispectral, and NDVI).

These modalities represent the cherry tree cultivation in many levels. Each modality describes the same object (cherry tree) within the dataset, i.e., for each tree within. For example, Fig. 2 (please refer to the ReadMe file) show RGB images, Fig. 3 (please refer to the ReadMe file) illustrates multispectral images, and Fig. 4 (please refer to the ReadMe file) provides UAV images. All images show the same cherry trees under three (RGB, multispectral, and UAV) aspects.

5. Dataset Collection & Annotation

This dataset was annotated by two agronomist experts in terms of disease stage (Armillaria). In particular, they annotated each cherry tree, one by one, in four levels of disease stage:

Healthy: the cherry tree is completely healthy;

Stage1: Armillaria is present in light form in the cherry tree;

Stage2: Armillaria is present in advanced form;

Stage3: the cherry tree is killed due to Armillaria.

The annotation process was considered by each one of the underlying modalities (RGB, multispectral and UAV/aerial).

5.1 Image Collection

The image collection is depicted in the following image (please refer to the ReadMe file) in terms of the three modalities (aerial / Unmanned Aerial Vehicle (UAV) images, ground RGB images/photos, and ground multispectral images/photos).

5.2 Dataset Overview

The dataset overview is depicted in Table 1 (please refer to the ReadMe file).

6. Structure and Format

6.1 Dataset Structure

The provided dataset has the following structure (please refer to the ReadMe file).

6.2 Guide to edit the *.tif files

The Aerial/UAV images contain images obtained from the UAV camera in the .tif format. To open these images, you will need the QGIS or other relevant program, or load them by using the corresponding python libraries. Please follow the steps below:

Open QGIS

Locate the browser window in QGIS

Navigate to the folder that contains the images and select all the images in the layer.

Once you have selected the images, select Add Layer to Project, and the selected image will be added to your map.

For accessing the Image data with the OpenCV python library the following code example is provided (please refer to the ReadMe file).

7. Acknowledgment

This work was co‐financed by the European Regional Development Fund of the European Union and Greek national funds through the Operational Program Competitiveness, Entrepreneurship and Innovation, under the call RESEARCH – CREATE – INNOVATE (project code: Τ1EDK-04759).

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreements No. 957406 (TERMINET).

References

[1] Devkota, P.; Iezzoni, A.; Gasic, K.; Reighard, G.; Hammerschmidt, R. Evaluation of the susceptibility of Prunus rootstock genotypes to Armillaria and Desarmillaria species. Eur. J. Plant Pathol. 2020, 158, 177–193.

[2] Devkota, P.; Hammerschmidt, R. “The infection process of Armillaria mellea and Armillaria solidipes”. Physiol. Mol. Plant Pathol. 2020, 112, 101543.

📌 Dataset Overview This dataset contains 500 images of tomato plants at two distinct growth stages, collected from the Tamil Nadu Agricultural University (TNAU) fields. The dataset is designed for deep learning-based classification of tomato plant growth stages, which helps in automating agricultural monitoring and decision-making.

📂 Dataset Structure Stage 1: Early Vegetative – 250 images 🌿 Stage 2: Flowering Initiation – 250 images 🌼 All images were captured under natural field conditions with varying lighting and environmental factors.

🎯 Applications Tomato plant growth stage classification Precision agriculture & smart farming Deep learning & computer vision research 🔍 Usage Instructions This dataset is ideal for training CNN models like ResNet50, VGG16, and EfficientNet.

python Copy Edit from tensorflow.keras.preprocessing.image import ImageDataGenerator

datagen = ImageDataGenerator(rescale=1./255) train_data = datagen.flow_from_directory('dataset/', target_size=(224,224), batch_size=32, class_mode='categorical') 📜 License This dataset is provided under CC BY 4.0 – You are free to use, modify, and share it with proper attribution.

The total collected data consists of 3,156 images categorized into 10 different types of pests and diseases on rice. Additionally, this data has been analyzed and evaluated by from Cuu Long Delta Rice Research Institute

SMART AGRICULTURE

## Overview

SMART AGRICULTURE is a dataset for instance segmentation tasks - it contains Objects annotations for 354 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

In the realm of global agriculture

This study aims to present a systematic literature review (SLR) to address the lack of a comprehensive review of the literature on cybersecurity in smart agriculture. This SLR analyzes 58 documents extracted from Scopus, Web of Science, and IEEE Xplore. The main findings on cybersecurity in smart agriculture encompass the challenges of cybersecurity in agriculture, the detection of attacks and intrusions, the evaluation of case studies, the assessment of frameworks, and the analysis of applied models. Organizations should also train their employees to recognize and respond to cyber threats.

Smart Farming

## Overview

Smart Farming is a dataset for object detection tasks - it contains Chilly annotations for 722 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

the ideal cycle is 14-18).

Annotated image dataset with different stages of European pear rust in orchards for UAV-based automatic symptom detection.

The evaluation of fruit genetic resources regarding a resistance to pathogens is an essential basis for subsequent selection in fruit breeding. Both genetic analysis and phenotyping of defined traits are important tools and provide decision data in the evaluation process. However, the phenotyping of plants is often carried out "by hand" and remains the bottleneck in fruit breeding and fruit growing. The development of a digital and UAV (unmanned aerial vehicle)-based phenotyping method for the assessment of genotype-specific susceptibility or resistance against diseases in orchards would significantly increase the efficiency of plant breeding. In this framework, a workflow for drone-based monitoring of pathogens in orchards was developed using the European pear rust (Gymnosporangium sabinae) as model pathogen. We provide a dataset with expert-annotated high-resolution RGB images with pear rust symptoms. The UAV images present different pear genotypes, including varieties, wild species and progeny from breeding. The dataset contains manually labelled images with a size of 768 x 768 pixels of leaves infected with pear rust at different stages of development, labelled as class GYMNSA, as well as background images without symptoms. A total of 584 annotated images and 162 background images, organized into a training and validation set, are included in the GYMNSA dataset. This dataset can be used as a resource for researchers and developers working on drone-based plant disease monitoring systems.

Success.ai’s Agricultural Data provides unparalleled access to verified profiles of agriculture and farming leaders worldwide. Sourced from over 700 million LinkedIn profiles, this dataset includes actionable insights and contact details for professionals shaping the global agricultural landscape. Whether your objective is to market agricultural products, establish partnerships, or analyze industry trends, Success.ai ensures your outreach is powered by accurate, enriched, and continuously updated data.

Why Choose Success.ai’s Agricultural Data? Comprehensive Professional Profiles

Access verified LinkedIn profiles of farm owners, agricultural consultants, supply chain managers, agribusiness executives, and industry leaders. AI-validated data ensures 99% accuracy, minimizing wasted outreach and improving communication efficiency. Global Coverage Across Agricultural Sectors

Includes professionals from crop farming, livestock production, agricultural technology, and sustainable farming practices. Covers key regions such as North America, Europe, APAC, South America, and Africa. Continuously Updated Dataset

Real-time updates reflect role changes, organizational shifts, and emerging trends in agriculture and farming. Tailored for Agricultural Insights

Enriched profiles include professional histories, areas of specialization, and industry affiliations for deeper audience understanding. Data Highlights: 700M+ Verified LinkedIn Profiles: Gain access to a global network of agricultural and farming professionals. 100M+ Work Emails: Communicate directly with decision-makers in agribusiness and farming. Enriched Professional Histories: Understand career trajectories, expertise, and organizational affiliations. Industry-Specific Segmentation: Target professionals in crop farming, agtech, and sustainable agriculture with precision filters. Key Features of the Dataset: Agriculture and Farming Professional Profiles

Identify and connect with farm operators, agricultural consultants, supply chain managers, and agribusiness leaders. Engage with professionals responsible for farm management, equipment procurement, and sustainable farming initiatives. Detailed Firmographic Data

Leverage insights into farm sizes, crop or livestock focus, geographic distribution, and operational scales. Customize outreach to align with specific farming practices or market needs. Advanced Filters for Precision Targeting

Refine searches by region, type of agriculture (crop farming, livestock, horticulture), or years of experience. Customize campaigns to address unique challenges such as climate adaptation or supply chain optimization. AI-Driven Enrichment

Enhanced datasets deliver actionable data for personalized campaigns, highlighting certifications, achievements, and key projects. Strategic Use Cases: Marketing Agricultural Products and Services

Promote farm equipment, crop protection solutions, or livestock management tools to decision-makers in agriculture. Engage with professionals seeking innovative solutions to enhance productivity and sustainability. Collaboration and Partnerships

Identify agricultural leaders for collaborations on sustainability programs, research projects, or community initiatives. Build partnerships with agribusinesses, cooperatives, or government bodies driving agricultural development. Market Research and Industry Analysis

Analyze trends in crop yields, livestock production, and agricultural technology adoption. Use insights to refine product development and marketing strategies tailored to evolving industry needs. Recruitment and Talent Acquisition

Target HR professionals and agricultural firms seeking skilled farm managers, agronomists, or agtech specialists. Support hiring for roles requiring agricultural expertise and leadership. Why Choose Success.ai? Best Price Guarantee

Access industry-leading Agricultural Data at the most competitive pricing, ensuring cost-effective campaigns and strategies. Seamless Integration

Easily integrate verified agricultural data into CRMs, recruitment platforms, or marketing systems using APIs or downloadable formats. AI-Validated Accuracy

Depend on 99% accurate data to minimize wasted outreach and maximize engagement outcomes. Customizable Solutions

Tailor datasets to specific agricultural segments, regions, or areas of focus to meet your strategic objectives. Strategic APIs for Enhanced Campaigns: Data Enrichment API

Enhance existing records with verified agricultural profiles to refine targeting and engagement. Lead Generation API

Automate lead generation for a consistent pipeline of qualified professionals in the agriculture sector, scaling your outreach efficiently. Success.ai’s Agricultural Data empowers you to connect with the leaders and innovators transforming global agriculture. With verified contact details, enriched professional profiles, and global reach, your marketing, partn...

The LTER annual crops (corn, soy and wheat), treatments 1-4, are harvested annually using a combine equipped with a GPS and precision agriculture software to allow detailed yield measurements with coincident GPS latitude and longitude data.. original data source http://lter.kbs.msu.edu/datasets/40 Resources in this dataset:Resource Title: Website Pointer to html file. File Name: Web Page, url: https://portal.edirepository.org/nis/mapbrowse?scope=knb-lter-kbs&identifier=37 Webpage with information and links to data files for download

This dataset was made by augmenting optimum soil and environmental characteristics for crop growth

The dataset contains soybean crop adult insect augmented cropped Images ( a total of 7306 images) in JPG format. There were considered four kind of soybean crop insect’s images as:

1. A folder Augmented_Cropped_Eocanthecona_Bug_A contains 1802 images of Eocanthecona Bug. The augmentation methods and corresponding images are as:

Brightness (contrast):201, flipping (horizontal):300, rotation (45 degree): 301, saturation: 102, scaling:300, shearing:299, translation:299

1. A folder Augmented_Cropped_Tobacco_Caterpillar_B contains 1812 images of Tobacco Caterpillar. The augmentation methods and corresponding images are as:

Brightness (contrast):200, flipping (horizontal):300, rotation (45 degree): 313, saturation: 101, scaling:300, shearing:299, translation:299

1. A folder Augmented_Cropped_Red_Hairy_Catterpillar_C Contains 1798 images of Red Hairy Caterpillar. The augmentation methods and corresponding images are as:

Brightness (contrast):200, flipping (horizontal):300, rotation (45 degree): 300, saturation: 100, scaling:300, shearing:299, translation:299

1. A folder Augmented_Cropped_Larva_Spodoptera_D contains 1894 images of Larva Spodoptera. The augmentation methods and corresponding images are as:

Brightness (contrast):201, flipping (horizontal):300, rotation (45 degree): 300, saturation: 101, scaling:300, shearing:299, translation:393

1. Initially, all the images were taken from the following two datasets and then further applied various augmentation methods (brightness, flipping, rotation, saturation, scaling, shearing, translation) to enhance the dataset size:

(i). Tiwari, Vivek; Saxena, Ravi R; Ojha, Muneendra (2020): Soybean Crop Insect Raw Image Dataset_V1 with Bounding boxes for Classification and Localization. figshare. Dataset. https://doi.org/10.6084/m9.figshare.13077221.v3

(ii) Tiwari, Vivek; Saxena, Ravi R; Ojha, Muneendra (2020): Soybean Crop Insect Processed (Cropped) Image Dataset_V1 for Classification. figshare. Dataset. https://doi.org/10.6084/m9.figshare.13078883

The dataset was developed by the authors under collaborative work between Indira Gandhi Krishi Vishwavidyalaya (IGKV), Raipur (CG), and DSPM IIIT Naya Raipur (CG), India

The Ministry of Agriculture, Food and Rural Affairs systematically provides production environment and operation information for each crop of smart farms. The data includes basic information on farmers and information on the cultivation period, and collects detailed environmental information such as temperature, humidity, and CO2, as well as control information such as nutrient solution, light, and irrigation. It is also structured to allow monitoring of crop growth status by integrating growth information and survey information by growth stage. Sample photos and consulting reports are also provided to support field application. It is useful for research on deriving optimal production conditions for each crop in the greenhouse and facility horticulture fields by analyzing the economic feasibility and operational efficiency of smart farms through the use of management information. This data contributes to promoting digital transformation of agricultural fields and supporting decision-making in smart farm fields.

Type of data: 504 x 1120 px mango images. Data format: JPEG. Contents of the dataset: Images (original, processed, and augmented) of common and popular varieties of mangoes in Bangladesh.

Number of classes: Fifteen (15) common and popular varieties of mangoes in Bangladesh - (1) Amrapali, (2) Ashshina Classic, (3) Ashshina Zhinuk, (4) Banana Mango, (5) Bari-4, (6) Bari-11, (7) Fazli Classic, (8) Fazli Shurmai, (9) Gourmoti, (10) Harivanga, (11) Himsagor, (12) Katimon, (13) Langra, (14) Rupali, and (15) Shada.

Number of images: Total number of images in the dataset: 28,515. (1) Total original (raw) images of mango cultivars (MangoOriginal) = 5,703, (2) Total processed images with a blend of both real and virtual backgrounds (MangoRealVirtual) = 5,703, and (3) Total augmented images (MangoAugmented)= 17,109.

Distribution of instances: (1) Original (raw) images in each class of the mango cultivars (MangoOriginal): Amrapali = 135, Ashshina Classic = 571, Ashshina Zhinuk = 1,286, Banana Mango = 83, Bari-4 = 74, Bari-11 = 1,244, Fazli Classic = 171, Fazli Shurmai = 247, Gourmoti = 630, Harivanga = 265, Himsagor = 106, Katimon = 424, Langra = 120, Rupali = 184, and Shada = 163. (2) Processed images with a blend of both real and virtual backgrounds for each class of the mango cultivars (MangoRealVirtual): Amrapali = 135, Ashshina Classic = 571, Ashshina Zhinuk = 1,286, Banana Mango = 83, Bari-4 = 74, Bari-11 = 1,244, Fazli Classic = 171, Fazli Shurmai = 247, Gourmoti = 630, Harivanga = 265, Himsagor = 106, Katimon = 424, Langra = 120, Rupali = 184, and Shada = 163. (3) Augmented images for each class of the mango cultivars (MangoAugmented): Amrapali = 405, Ashshina Classic = 1,713, Ashshina Zhinuk = 3,858, Banana Mango = 249, Bari-4 = 222, Bari-11 = 3,732, Fazli Classic = 513, Fazli Shurmai = 741, Gourmoti = 1,890, Harivanga = 795, Himsagor = 318, Katimon = 1,272, Langra = 360, Rupali = 552, and Shada = 489.

Dataset size: Total size of the dataset = 1.35 GB and the compressed ZIP file size = 1.16 GB.

Data acquisition process: Images of various mango varieties are captured through high-definition smartphone cameras focusing from different angles.

Data source location: Local wholesale and retail fruit markets located in six geographically distributed districts of Bangladesh, namely Chapai Nawabganj, Dhaka, Panchagarh, Rajshahi, Rangpur, and Satkhira which are renowned for diverse mango cultivation and availability.

Where applicable: Training and evaluating machine learning and deep learning models to identify and classify mango varieties in Bangladesh which can be useful in smart horticulture, precision farming, supply chain automation, ecology and ecosystem health monitoring, and biodiversity and conservation efforts.