crop classification using deep learning on satellite images

Set of Machine Learning Algorithms developed with the aim of determining health states of different types of crops

An app made for Smart India Hackathon 2018. An idea to help farmers of India to sell their products at much higher rate and with ease. With a vision to positively impact agriculture industry in India.

Agricultural Monitoring exploiting Sentinel 1 and Sentinel 2. SandboxNL contains detailed explanations about the creation and usage of the parcel based Sentinel datasets.

Predicting rice field yields through the integration of Microsoft Planetary satellite images, meteorological data, and field information in the 2023 EY Open Science Data Challenge - Crop Forecasting.

Agricultural Land Use Evaluation System

An R package for simulating Generalised Management Strategy Evaluation

Estimating shapes and volumes of Capsicum fruits (bell pepper) by fitting superellipsoids to 3D mapping data for autonomous crop monitoring tasks for ROS1

Materials for NCEO crop modelling, Earth Observation and DA workshop in Accra

Caloric Suitability Index

Comprehensive database for diazotroph nitrogenases, alternative nitrogenases, and nitrogenase-like enzymes at the University of North Carolina at Charlotte (UNCC)

Correlation for African Soil between chemistry and fertility data using Logistic Regression. Treatment of infrared (FTIR) spectra by machine learning.

Scripts associated to the paper to be published

A basic simulation of a coffee operation.

Processor showcasing how to compare vegetation index before and after an event to determine impacted areas.

CuHacking, TAMUhack Winner - AI Cassava Plant Disease Detector

A website that allows farmers to input their soil and location details and get a recommendation for the crop to grow and fertilizer to use, using machine learning models.

Developed an android mobile app (GreenFinder), trained, and evaluated two deep learning image classification models for the use-case. The mobile app classifies scanned fruits, vegetables and flowers, as well as provides knowledgeable information on each classified item.

The traditional in-situ soil analysis methods are laborious & inefficient, limiting scalability and hindering timely access to crucial soil data for optimal fertilization by farmers. In the amazing challenge, we tried to predict soil parameters(Phosphorous, Potassium, Magnesium and pH)from hyperspectral satellite images.