Satellite Imagery For

Agriculture &
Forestry

agri

Optimising Crops With Precision imagery

Evaluate vegetation health

Valuable multispectral bands allow in-depth analysis of plant and soil conditions

Study Land
Use

VHR imagery gives you the power to map land use at wide scales with incredible detail and accuracy

Manage Food Security

Mapping crops and analysing harvests on regional scales ensures that agricultural goals are being maintined

There is a strong requirement for monitoring forests and crops in order to tackle the present challenges within agriculture and forestry. Near real-time monitoring is crucial to react to extreme events – such as climate conditions or pest infestations – and thus minimize their impact, while also optimising management practices – such as precision agriculture – in a sustainable manner.

Very High Resolution (VHR) optical satellite imagery can be an essential tool to respond to threats against agriculture and forestry as it offers a non-destructive mean of proving recurrent information from both a local and global scale. European Space Imaging has particularly excelled at large collections in challenging weather conditions. Europe has a diverse climate with many regions blanketed in clouds for much of the year. The unique real-time weather monitoring by our operations team has ensured success for the most demanding projects.

Optimising wine harvest Using satellite imagery to monitor grape vigor during the Véraison period

Read about this and more satellite imagery applications in the Agriculture & Forestry INCITE industry report: Seeing Through the Trees – Monitoring Agriculture and Forestry Using Satellite Imagery

MANAGE SUSTAINABILITY

Very high resolution satellite imagery is detailed enough to show individual trees, which allows precise monitoring of forest and crop assets. It is ideal for:

  • Detecting illegal logging
  • Estimating the number of trees in a forest
  • Calculating carbon stocks
  • Identifying tree stress and pest infections
  • Supporting firefighting efforts
  • Protection of natural forests

PRECISION AGRICULTURE

We offer more spectral diversity and better spatial resolution than any other satellite imagery provider – allowing you to see more of what is actually happening on your land. A near-infrared (NIR) image like this one shows the healthy vegetation as red, and is sensitive enough to discriminate between types of plants, their stage of maturity, and changes in plant health before they are visible to the human eye. This enables:

  • Early warning of health problems
  • Data for calculating yield
  • Optimising harvest timing
  • Monitoring of weeds, insect pests, or diseases
  • Irrigation system planning and inspection
  • Managing water resources and soil quality

Learn More About

RESPOND TO CHANGE

VHR satellite images can be used in software utilizing Artificial Intelligence (AI) to automatically detect and analyse changes over time. This rapidly growing technology offers “off-the-shelf” solutions for a number of applications including:

  • Ensuring global food security
  • Extracting trends in plant health and productivity
  • Validating activity and compliance
  • Localizing inputs such as fertilizer
  • Smart and timely management decisions

Learn More About

Download the Latest Edition of INCITE

Seeing Through the Trees: Monitoring Agriculture and Forestry Using Satellite Imagery

The definitive guide to acquiring and using satellite imagery in the agriculture & forestry industry.

Discover
What's

NEW

Scroll to Top

Architecture of ResNet34-UNet model

UNet architecture for semantic segmentation with ResNet34 as encoder or feature extraction part. ResNet34 is used as an encoder or feature extractor in the contracting path and the corresponding symmetric expanding path predicts the dense segmentation output.

Architecture of VGG16-UNet model

UNet architecture for semantic segmentation with VGG16 as the encoder or feature extractor. VGG16 is used as an encoder or feature extractor in the contracting path and the corresponding symmetric expanding path predicts the dense segmentation output.

Architecture of ResNet34-FCN model

In this model, ResNet34 is used for feature extraction and the FCN operation remains as is. The feature of ResNet architecture is exploited where just like VGG, as the number of filters double, the feature map size gets halved. This gives a similarity to VGG and ResNet architecture while supporting deeper architecture and addressing the issue of vanishing gradients while also being faster. The fully connected layer at the output of ResNet34 is not used and instead converted to fully convolutional layer by means of 1×1 convolution.

Architecture of VGG16-FCN model

In this model, VGG16 is used for feature extraction which also performs the function of an encoder. The fully connected layer of the VGG16 is not used and instead converted to fully convolutional layer by means of 1×1 convolution.

X