Data science in Agriculture | Data Science in Agriculture

Crop modeling and remote sensing

Sat, 14 Aug 2021 00:00:00 +0000

Crop modeling helps the scientist to understand the basic interactions of soil, plant, and atmosphere. Predictions can be made based on the assessment of current and expected crop performance. This requires the past and the present weather and crop data to predict the performance in the future.

Our project aims to map crop type classification incorporating crop modeling simulations and remote sensing data for crop type classification.

For this project we have being utilized APSIM crop model for generate simulations of soybean and corn growth for retrieve variables to combine with remote sensing data to build a data set for crop type classification in Northwest Rio Grande do Sul, Brazil.

Crop summer rotation

Sat, 14 Aug 2021 00:00:00 +0000

Crop rotation is the practice of growing a series of different types of crops in the same area across a sequence of growing seasons. It reduces reliance on one set of nutrients, pest and weed pressure, and the probability of developing resistant pest and weeds. Continuous crop in the same place for many years in a row, known as monocropping, gradually depletes the soil health and selects for a highly competitive pest and weed community.

Our project aims to map crop rotation practices utilizing ground truth and remote sensing data.

For this project we have being utilized crop type classification model to extract crop type information of 4 growing seasons in a row for evaluate the crop rotation pattern in the different regions in Rio Grande do Sul, Brazil.

Crop type classification

Sat, 14 Aug 2021 00:00:00 +0000

Crop type classification is essential for agricultural management and policy making for food security and sustainability. Automating crop classification process while elaborating a workflow is a key step for reliable and precise crop mapping.

Our project aims to develop a in-season crop type map for the main crops in Southern Brazil.

For this project we have being utilized data from Google Street View and ground truth data incorporation data fusion data from Sentinel-1, Sentinel-2 and SRTM data to develop a machine learning model to estimate crop area and generate crop type maps.