Réseaux Sociaux

Maulik Raval

Building Agri Check — a low-cost, smartphone-based app to help farmers test soil health and (soon) detect crop diseases. Free/open tools only, since it's a student project aimed at real farmers. Two things I'd love help with from my network: 1) Plant disease detection — what's the best free platform to train an image-classification model for crop leaf diseases? I've used Google Teachable Machine for simple classification before — is that enough for disease detection, or do I need something more (Roboflow, Kaggle notebooks, Colab + a pretrained model)? Pointers to good free labelled leaf-disease datasets would help too. 2) Soil NPK/pH testing — my app reads a colour-changing chemical reagent via the camera to estimate Nitrogen, Phosphorus, Potassium and pH. Still deciding: train on 4 separate photos (one reagent tube per nutrient), or 1 photo of a multi-pad strip with all 4 colours at once? Would appreciate real experience if you've built something similar. Open to DMs, comments, or just pointing me to the right resource 🙏 #AgriTech #MachineLearning #ComputerVision #TeachableMachine #OpenSource

Meni O

🌱 AI-Based Crop Recommendation System | Machine Learning Project I’m pleased to share my internship project: “AI-Based Crop Recommendation System — A Machine Learning Approach for Bihar’s Agro-Climatic Conditions.” The objective of this project was to build an ML-based system that recommends suitable crops using soil and climatic conditions. 🌾 Input & Prediction The model uses 7 parameters: • Nitrogen (N) • Phosphorus (P) • Potassium (K) • Temperature • Humidity • Soil pH • Rainfall It predicts among 8 crops: Rice, Wheat, Maize, Lentil, Mustard, Sugarcane, Jute and Potato. The "recommend()" function provides the Top-3 crop recommendations with model confidence values. 📊 Dataset & Methodology I created a simulated dataset of 3,200 records, with 400 samples per crop. The data was divided into 80% training (2,560) and 20% testing (640) using a stratified split. I compared six classification algorithms: Logistic Regression, KNN, SVM, Decision Tree, Random Forest and Gradient Boosting. For preprocessing, I used StandardScaler inside a Pipeline to avoid data leakage. Model selection was performed using Stratified 5-Fold Cross-Validation, followed by hyperparameter tuning with GridSearchCV. 🤖 Best Model & Results SVM with an RBF kernel achieved the highest cross-validation performance: CV Accuracy: 93.52% ± 0.79% After tuning, the final model achieved on the untouched test set: 🎯 Accuracy: 93.12% 📌 Macro F1: 93.13% 🔥 Top-3 Accuracy: 100% I also performed error analysis. Out of 44 misclassified test samples, 26 involved confusion between Jute and Rice, which showed where the model had difficulty distinguishing overlapping simulated conditions. I further explored permutation importance and feature ablation to understand the contribution of different features. 🎓 What I Learned This project taught me that building an ML model is not just about achieving high accuracy. I learned how to prepare reproducible data, apply preprocessing correctly, compare multiple algorithms, and use cross-validation and hyperparameter tuning for model selection. Error analysis, feature importance and ablation studies helped me understand why the model performs the way it does, rather than looking only at the final accuracy. Most importantly, I learned to evaluate the data quality, methodology and limitations before interpreting an ML result. ⚠️ Important Note The dataset used in this project is simulated, not collected from real farms. Therefore, the 93.12% accuracy demonstrates the model's performance on the simulated dataset and should not be interpreted as real-world agricultural accuracy. This project gave me practical exposure to the complete ML workflow — from data preparation and preprocessing to model selection, evaluation, error analysis and prediction. #ArtificialIntelligence #MachineLearning #Python #DataScience #AgriTech #AI #ML #Internship #CropRecommendation #ScikitLearn #SVM #GECGopalganj

Sam

@sam489564164015

60,000 sqm of plant space ensures one-stop manufacturing and delivery. Eliminate capacity guesswork for your next season. Explore our intelligent manufacturing capabilities: https://t.co/YXdrenoQg1 #AgriTech #SupplyChain #Manufacturing https://t.co/INj9VIxayb

Mark™️

@thatoptometrist

📢 Cornell University - CALS, Dr. Ke Wang Lab HIRING Fully Funded Postdoc - Bioengineering and Precision Fermentation 🔬 Precision fermentation, alternative protein, biomanufacturing, biotech & circular bioeconomy | Food Science at Cornell AgriTech, Geneva, NY | 100% onsite, https://t.co/TqdUR4LuZu

Şerif Altındal

@serifaltindal

🍅🤖 Tarımda teknoloji artık geleceğin değil, bugünün konusu. Redworld Technology olarak geliştirdiğimiz otonom domates toplama robotuyla; yapay zekâ, görüntü işleme ve robotik teknolojilerini doğrudan sahaya taşıyoruz. Üretmeye ve geliştirmeye devam. 🇹🇷 #RedworldTechnology https://t.co/QyteOofrVm

JBKlutse.com

Ghana has nearly 800,000 registered cocoa farmers. Cocoa is the country's biggest export crop. And yet, many of those farmers wait months to receive payment after selling their harvest — simply because cocoa buying companies can't always access working capital fast enough to pay them upfront. Two deals announced this week attempt to fix that at scale. The International Finance Corporation (IFC) has entered a risk-sharing partnership with Absa Bank Ghana, committing up to USD 50 million — which enables Absa to deploy up to USD 200 million in lending to licensed cocoa buying companies. The idea is straightforward: better-capitalised buying companies pay farmers faster and more reliably across the buying season. The deal also includes a push for climate-aligned, traceable cocoa sourcing. Separately, IFC is partnering with Complete Farmer — a Ghanaian agritech startup — to bring fintech-enabled agricultural loans directly to smallholder farmers. The technology helps extend credit to farmers who don't fit the traditional banking mould, using farm data and digital infrastructure to assess creditworthiness. Combined target: support for 240,000 smallholder farmers by 2030. What stands out to me is the layered approach. One mechanism finances the intermediaries (buying companies). The other goes directly to the farmer. Together, they address two separate chokepoints in the same supply chain. "By 2030" targets always deserve scrutiny — execution matters more than announcements. But the architecture here is more thoughtful than the typical development finance press release. Ghana's agricultural sector contributes significantly to GDP and rural livelihoods. Access to finance has consistently been identified as the primary barrier to productivity growth among smallholders. If these partnerships deliver even half their stated targets, the ripple effects on food security and rural incomes would be meaningful. Full breakdown on JBKlutse — link in first comment. For those working in agriculture, development finance, or fintech across Africa: what do you think is the hardest part of getting credit products to actually reach smallholder farmers at scale? #jbklutse #agricultureghana #agrifinance #ghanafintech #IFC

AgroCarbonX

Un agricultor español con 100 hectáreas deja ir 13.800€ al año. Sin saberlo. 😶 No porque trabaje mal. Sino porque nadie le ha dado la herramienta para cobrar lo que ya tiene derecho a cobrar. Sus ayudas PAC sin reclamar. Sus créditos de carbono sin certificar. Su suelo capturando valor cada día — invisible. Lo cambiamos con un robot que cabe en una mochila, cuesta menos de fabricar que un iPhone Pro, y lo sueltas en la parcela sin tocar nada más. 🤖🌱 Él trabaja. Tú cobras. Eso es TerraBot y AgroCarbonX. 🔗 agrocarbonx.com #AgriTech #Agricultura #Carbono #CRCF #Startup #Sostenibilidad

Pablo Santana

How do you transition from simply predicting crop failure to actively prescribing the mathematical solution to prevent it? 🌱🤖 Modern hydroponic systems generate massive amounts of IoT telemetry data, yet the agribusiness sector frequently struggles to utilize this information prescriptively. Traditional linear models fail to capture the severe, non-linear biological thresholds of crop decay. o solve this, I recently developed an End-to-End AgriTech Decision Intelligence Engine. Moving beyond passive dashboards, I architected a mathematical pipeline that bridges Machine Learning with Operations Research: 1️⃣ Data Topology: I audited 4,900 telemetry records to isolate operational "sweet spots" and accurately impute missingness mechanisms caused by environmental stress. 2️⃣ Predictive Modeling & XAI: Deploying a non-linear Ensamble (Random Forest Regressor) achieving 94.5% accuracy (R²). Game Theory (SHAP) was integrated to map the exact causal directionality of biochemical drivers. 3️⃣ Prescriptive Optimization: Building a Heuristic Grid Search engine. By freezing uncontrollable weather variables, the engine simulates over 10,000 biochemical realities in milliseconds to extract the optimal operational parameters. The culmination of this research is a fully interactive Digital Twin built with Streamlit. Rather than just forecasting a yield, the system calculates the absolute global maximum and prescribes the exact actuator commands (e.g., "Adjust pH to 6.0") needed to rescue the crop. Swipe through the document below to explore the architectural pipeline and mathematical framework driving this engine. 👇 #DataScience #MachineLearning #AgriTech #DecisionIntelligence #Python #OperationsResearch #Streamlit #PrescriptiveAnalytics

Mariano Larrazabal

@agrobialar

The VISION Conference, now in its seventh year, is once again set to revolutionize the ag tech landscape. The post Unlocking the Value of Innovation: VISION 2024 Shaping the Future of Ag ... @GlobalAgTech #Agtech #Agritech  https://t.co/Tv0izx5VzB

Navotthan Startup Foundation, REC Kannauj

Proud to see ClimAgro Analytics showcasing its AI-driven solutions for climate-resilient agriculture at AI Manthan 2.0, National AI Innovation Summit, hosted at Chhatrapati Shahu Ji Maharaj University (CSJMU), Kanpur. It is encouraging to see technology being translated into practical solutions for farmers, supporting better irrigation decisions, climate-risk preparedness, crop planning and access to emerging opportunities such as carbon credits. We are especially delighted that the team had the opportunity to present its work before Hon’ble Governor of Uttar Pradesh, Smt. Anandiben Patel, and receive appreciation for its efforts toward strengthening climate resilience in Indian agriculture. We also extend our sincere thanks to Dr. Mahip Singh, CEO, Innovation Hub UP, for visiting the startup stall, interacting with the team, and encouraging their efforts toward building impactful AI-driven solutions for agriculture. At Navotthan Startup Foundation, REC Kannauj, we remain committed to supporting innovators and startups working on meaningful, technology-driven solutions with real-world impact. Congratulations to the ClimAgro Analytics team. Wishing you continued success and many more milestones ahead. 🚀🌱 #NavotthanStartupFoundation #RECKannauj #ClimAgroAnalytics #AIManthan #ArtificialIntelligence #AgriTech #ClimateTech #StartupEcosystem #Innovation #UttarPradesh #Entrepreneurship REC KANNAUJ | TPC REC, Kannauj | E-Cell REC Kannauj | Innovation Hub UP | Chhatrapati Shahu Ji Maharaj Innovation Foundation, Kanpur | Uttar Pradesh Startup Mission (Official) | MeitY Startup Hub | Atal Innovation Mission Official | MoE's Innovation Cell | Dr. Harshit Mishra | Prof. Manoj Kr. Shukla | Dr. Ravish Singh Rajput | B D K Patro | Kiran Kumari | Saurabh Yadav

Bhargob Baro

Big Win for Team BlackCaps at the Smart India Hackathon (SIH) Internal Round! We are incredibly excited and proud to share that Team BlackCaps has successfully won the Internal Round of the Smart India Hackathon (SIH). What makes this achievement even more special is that we are all first-year students, taking our very first step into the world of hackathons, innovation, and real-world problem solving. Our Problem Statement: Early Detection and Management of Crop Diseases and Pest Infestations Our goal was to develop a solution that can help detect crop diseases and pest infestations at an early stage, enabling timely management and potentially reducing crop losses. From exploring ideas and research to development, debugging, and presenting, this journey taught us more than the classroom ever could. Despite challenges and doubts, we kept learning, improving, and moving forward together as a team. This victory is not just about winning an internal round. It represents the hard work, teamwork, creativity, and dedication of every member. Team BlackCaps Team Leader: Bhargob Baro Team Members: 1. Govind Durgam 2. Shweta Arya 3. Anshika 4. Avinash Dubey 5. Ansh Chopra Let’s keep learning. Let’s keep building. Let’s keep growing. Nit Agartala (MCA) #SmartIndiaHackathon #SIH #TeamBlackCaps #Hackathon #Agriculture #AgriTech #CropProtection #Innovation #FirstYear #StudentInnovation #Teamwork #Technology #ProblemSolving

Mohamed Maassou

PEROXYLINE : une solution performante pour l’hygiène et la désinfection en agriculture. PEROXYLINE associe l’acide peracétique (15,5 %) et le peroxyde d’hydrogène (40 %) pour agir par oxydation sur les micro-organismes. Une solution adaptée à la désinfection des surfaces, équipements et circuits, notamment dans les exploitations agricoles et les serres. 🧪 L’hygiène et la maîtrise sanitaire sont des éléments essentiels pour préserver la qualité des cultures et sécuriser les processus de production. IBES (International Biological and Ecological Solutions) Des solutions pour une agriculture plus sûre et plus performante.

Mohammad Belal Uddin

Dyson is famous for vacuum cleaners. But now it’s growing strawberries in a completely different way. 🍓🤯 Hidden behind the Dyson brand is a 26-acre strawberry farm designed around a fascinating idea: What if every plant could get more of the sunlight it needs? The farm uses a rotating vertical growing system that moves more than 1.2 million strawberry plants, helping distribute sunlight across the crops. And the reported result? 🍓 Up to 250% higher yields from the new vertical system. This is more than a strawberry farm. It’s a glimpse into how engineering, automation and agriculture could work together to produce more food from limited space. Dyson started by rethinking how we clean our homes. Now, it’s experimenting with how we grow our food. The future of farming may not just be about bigger fields. It may be about smarter ones. 🌱 Would you eat strawberries grown in a high-tech vertical farm? #Dyson #AgriTech #VerticalFarming #Innovation #FutureOfFood #SustainableAgriculture #Technology #Sustainability

Vaibhav Sharma

🚀 One experience, many lessons. Our team Code of Threads recently participated in BU SIH ’26 at Bennett University. We worked on AgriCareGuard, a project focused on using AI to help farmers detect crop diseases and pests at an early stage and receive better crop-health recommendations by considering factors such as soil and weather conditions. 🌱 Researching a real-world problem, building a solution, working together under deadlines, facing challenges, and presenting our idea taught us a lot. This experience helped us understand that every challenge is an opportunity to learn, improve, and come back stronger. A special shoutout to my teammates Arsh Sheikh, Harshit Sharma, Nihal Devarashetty, Vanshika . , Kumari Reshma for the teamwork, effort, and support throughout this journey. 🤝 This is just one step in our journey. More to build, more to learn. 🌱💻 #BUSIH26 #CodeOfThreads #AgriCareGuard #Hackathon #AI #AgriTech #LearningByBuilding #Teamwork #Innovation

👤

Samruddhi Tanagwade

𝐕𝐞𝐫𝐭𝐢𝐜𝐚𝐥 𝐅𝐚𝐫𝐦𝐢𝐧𝐠 𝐓𝐞𝐜𝐡𝐧𝐨𝐥𝐨𝐠𝐲 𝐌𝐚𝐫𝐤𝐞𝐭 𝟐𝟎𝟐𝟒-𝟐𝟎𝟑𝟐: 🌱📈𝐆𝐥𝐨𝐛𝐚𝐥 𝐑𝐞𝐬𝐞𝐚𝐫𝐜𝐡 𝐑𝐞𝐩𝐨𝐫𝐭. 𝐑𝐞𝐪𝐮𝐞𝐬𝐭 𝐟𝐨𝐫 𝐒𝐚𝐦𝐩𝐥𝐞 𝐂𝐨𝐩𝐲: https://lnkd.in/girJj4P3 With global food demand continuously rising and land for traditional farming shrinking, vertical farming has emerged as a revolutionary solution. The Vertical Farming Technology Market is expected to grow at an impressive CAGR of 25.3% from 2023 to 2032. Valued at $6.9 billion in 2023, it is projected to reach $22.2 billion by 2032. 🌍 Vertical farming leverages advanced technologies such as IoT, automation, and hydroponics to boost crop yields without requiring vast tracts of land, making it a sustainable solution for urban and resource-limited areas. Our latest report provides both quantitative and qualitative aspects of the Vertical Farming Technology Market, examining manufacturers, regional analysis, types, and applications. 📊 The report includes insights into market dynamics, industry trends, and competitive landscapes. Profiles of leading companies, product examples, and market share estimates for top competitors in 2024 are also featured. Segment-wise growth calculations and forecasts for consumption value are presented for the period 2024-2032, aiding businesses in targeting specific and lucrative market niches for the expansion of the Vertical Farming Technology Market. 𝐓𝐨 𝐊𝐧𝐨𝐰 𝐆𝐥𝐨𝐛𝐚𝐥 𝐒𝐜𝐨𝐩𝐞 𝐚𝐧𝐝 𝐃𝐞𝐦𝐚𝐧𝐝 𝐨𝐟 𝐕𝐞𝐫𝐭𝐢𝐜𝐚𝐥 𝐅𝐚𝐫𝐦𝐢𝐧𝐠 𝐓𝐞𝐜𝐡𝐧𝐨𝐥𝐨𝐠𝐲🌱📈. 𝐑𝐞𝐪𝐮𝐞𝐬𝐭 𝐟𝐨𝐫 𝐒𝐚𝐦𝐩𝐥𝐞 𝐂𝐨𝐩𝐲: https://lnkd.in/girJj4P3 By Type: Hydroponics, Aeroponics, Aquaponics, Others By Application: Commercial, Residential, Industrial, Institutional, Others By Region: North America, Europe, Asia-Pacific, South America, Middle East & Africa By Key Players: Plenty®, AeroFarms, Bowery Farming, INFARM, AppHarvest, Kalera, BrightFarms, Freight Farms, Sky Greens Canada, Spread Tecnologia., Agrilutions, LettUs Grow, iFarm, Future Crops, Fujitsu, N.THING Inc, Vertical Future, Square Roots, Vfarm, 80 Acres Farms, Iron ox, Green Sense Farms, LLC, Nova Farms, Vertical Field, INNO-3B, JFS Altius Farms, Eden Green Technology, SHIGEHARU HIGASHI, Planet Farms, Bob Forward, Agritecture, Cropbox, Nuvonic, EcoVadis, Heliospectra Smart LED Lighting, OSRAM Digital Systems, Signify, Orbia, Blue Radix, Urban Crop Solutions #verticalfarming #sustainablefarming #futureofagriculture #agritech #urbanfarming #hydroponics #smartfarming #indoorfarming #aeroponics #greenfarming #technologyinnovation #futurefood #smartagriculture #climatechange #agriculturetech #croptechnology #urbanagriculture #agribusiness #farmingtech #marketresearch

Its Rakib

@itsrakib2007

What if robots could help replace missing bees? These mini robotic drones are designed to move between crops and mimic natural pollination. The goal: Help farmers protect yields as natural pollinator populations decline. #ai #robotics #smartfarming #agritech #innovation https://t.co/rBdpSDXP79