AI Impact Summit

Global AI Impact Commons

DeepLeaf - End-to-End Crop Health Management

DeepLeaf - End-to-End Crop Health Management

Morocco flag

Morocco

Agriculture

High replicability and adaption

Implementing Organisation

Deep Leaf

Morocco, Casablanca-Settat, Sidi Bennour

Private Sector

Implementing Point of Contact

El Mahdi Aboulmanadel

Founder and Chief Executive Officer

Contributor of the Impact Story

Deep Leaf

Year of implementation

2023

Problem statement

Late and inaccurate detection of crop diseases, pests, and nutrient stress leads to $300B in annual global losses, with 40% crop losses in Africa and Asia. 80% of smallholders lack access to expert agronomic advice. Current solutions are fragmented and reactive: satellite companies show indices but stop there, IoT solutions cost $2,500+ per site and do not scale, and agronomists are expensive and not always available. Farmers spray entire fields uniformly, wasting chemicals with no guidance on treatment timing or residue management. DeepLeaf AI enables early, accurate, and scalable crop health diagnosis using AI-powered image analysis, satellite monitoring, and expert knowledge systems-providing full accompaniment from planning to certified, residue-free harvest.

Impact story details

DeepLeaf is an agritech company developing AI-driven solutions for early detection and management of crop health risks. Its software uses computer vision and machine learning models trained on large-scale plant image datasets to identify diseases, pests, and nutrient deficiencies across diverse crops. The platform provides end-to-end farm management from planning to certified harvest, using satellite imagery (Sentinel-1/2), weather data, and AI-powered diagnostics. DeepLeaf serves farmers of all scales-from smallholders to large commercial operations-through accessible channels including WhatsApp, USSD, mobile apps, and web dashboards. The company focuses on reducing chemical inputs by 60-80% through precision agriculture while ensuring zero residues at harvest through automated pre-harvest interval compliance.

AI Technology Used

Computer Vision
Machine Learning
Remote Sensing Analytics
Predictive Analytics

Key Outcomes

Efficiency

Productivity, Economic Value Creation, Access

Reach, Accuracy

Quality Improvement, Resource Efficiency, Resilience

Risk Reduction

Impact Metrics

Accuracy in detecting crop diseases, pests, and nutrient deficiencies

Post-Implementation

0

Reduction in pesticide application through precision targeting

Post-Implementation

0

Improvement in crop yield through optimized treatment and early intervention

Post-Implementation

0

Implementation Context

Deployed

Africa (Morocco, Kenya), Middle East (Qatar partnership), expanding to Turkey and Mexico

Smallholder farmers (1-5 ha), commercial farms (50-500 ha), and large-scale operations (10,000+ ha). Focus on underserved rural farming communities including women farmers and youth in agriculture across Africa and the Global South

Key Partnerships

Private Sector: Hassad Food (Qatar), MTN Chenosis, Les Domaines Agricoles. Programs: BRAIN by Open Startup, GIZ SAIS, TASMU Accelerator, QDB Talent Community Program, Katapult Africa Climate Program, AWS/Deloitte Social Entrepreneur Accelerator 2025

Replicability & Adaptation

High (Proven in multiple contexts with minimal adaptation)

Platform is designed for rapid context adaptation: supports 57 crops with localized crop databases; provides local language interfaces via WhatsApp, USSD, and SMS; maintains country-specific product authorization databases (500+ active ingredients, 1000+ products per country); satellite-first approach works anywhere on Earth with zero hardware requirements; scales from 1 hectare smallholdings to 100,000+ hectare operations; optional IoT sensors and drones can be added for higher precision when needed (greenhouses, high-value crops).

* The data presented is self-reported by the respective organisations. Readers should consult the original sources for further details.