Agriculture

• Development of specialized methods for visualizing agrochemical indicators. Based on field samples, as well as terrain and soil data, the obtained results must be accurately interpolated. The next stage involves the development of management materials for proper agricultural activity. For example, the delimitation of management zones within fields.
• Developing a plan for the application of agrochemical products, with integration into chemical manufacturers’ catalogs to automate the ordering process.

• Sampling and Laboratory Tests
• Results of soil parameters mapping (soil type, soil moisture, pH, temperature, and agrochemical concentrations)
• Geospatial data (DEM, fields boundaries, imagery)

• GDAL/OGR
• QGIS
• ArcGIS
• Leaflet
• SciPy
• PyKrige
• Gstat
• GeoPandas

• Monitoring the condition of seedlings and the absence of deviations from the vegetation cycle (automated calculation of vegetation indices, etc.).
• Identification of adverse conditions in the fields (diseases, weeds, pests).
• Planning of fieldwork.
• Automation of agronomist record-keeping.
• Monitoring based on data from various sources (combination of data obtained from different satellite sensors, adding UAV and ground data results).

Plant health monitoring

• Spectral Analysis (vegetation indices calculation, stressors identification
• Thermal imaging (water stress and plant disease identification)
• Hyperspectral Imaging
• Machine Learning Models application
• IoT and In-Field Sensors

Yield Prediction

• Historical Yield Data Analysis (environmental, climatic, and management variables)
• Weather and Climate Modeling (simulation of the conditions affecting growth)
• Growth Models – process-based models (DSSAT, APSIM), Empirical Models
• Machine Learning
• Geospatial Analysis

• Remote Sensing Data (satellite, aerial, UAV), and derived indexes (for example: NDVI, EVI, REI, TSI)
• In-Field Sensor Data (Soil Data, Plant Data, Weather Data)
• Yield Data (Historical Yields, Crop-Specific Metrics)

• GDAL/OGR
• QGIS
• ArcGIS
• Leaflet
• SciPy
• PyKrige
• Gstat
• GeoPandas

• Integration and visualization of data from precision agriculture sensors, such as moisture indicators, stationary cameras, and more.
• Integration with agricultural equipment (e.g., irrigation systems).
• Solutions for greenhouses (sensors, lighting regulation, development of digital twins for greenhouses) and vertical farms.

Classic agriculture

• Soil monitoring (soil moisture, temperature, pH, and nutrient levels monitoring)
• Livestock monitoring (wearable devices for health tracking, location, and activity levels)
• Irrigation and Fertilization Automation (watering schedules based on sensor feedback)

Greenhouses

• Environmental Control (light, temperature, humidity, and CO2 levels)
• Actuators control HVAC systems, shading, and ventilation
• Hydroponics and Aeroponics (Automated nutrient dosing and water circulation)
• Disease Prevention

Vertical Farming

• Lighting Control (LED systems control, based on growth stages)
• Resource Management (water, nutrient, and energy consumption control)
• Automation and Robotics (automated seeding, harvesting, and maintenance)

• Short-Range (Bluetooth, Wi-Fi, Zigbee)
• Long-Range (LoRaWAN, Sigfox, Narrowband IoT, LTE-M)
• Wired protocols (RS-485, MODBUS)
• Internet-Based (MQTT, CoAP)

• IoT Frameworks (ThingsBoard, Node-RED, Kaa IoT, AWS IoT Core)
• Communication Libraries (Paho MQTT, CoAPy, LoRa Libraries)
• Sensor Integration (Adafruit CircuitPython, PySerial)
• Data Processing and Analytics (NumPy / Pandas, Scikit-Learn / TensorFlow, Apache Kafka)
• Visualization (Grafana, Plotly / Dash, Kepler.gl, QGIS, ArcGIS)

• Integration with weather services
• Integration with analytics platforms (crop conditions, crop prediction, etc.)
• Integration with the client’s existing solutions (accounting, asset management)

• API-Based Integration (use of available APIs and development of custom ones)
• Data aggregation (Combination of the data, received externally, with local data sources (client’s weather, soil sensors, drone imagery, information about crops, agrochemical activities) for comprehensive insights.
• Use and development of middleware solutions.

• Weather time-series data: temperature, humidity, rainfall, wind speed, solar radiation, etc.
• Analytics platforms:
  • Geospatial Data (vegetation indices, crop classification, alerted areas on fields);
  • Time-Series Data (Soil moisture, temperature, crop growth stages);
  • Agronomic Data (fertilizer applications, pesticide usage, crop yields).
• Current client’s software applications: financial, asset, operation data etc.

• Weather: OpenWeatherMap, WeatherStack, Climacell (Tomorrow.io), NOAA.
• Agro Analytics: Climate FieldView, Granular, Trimble Ag Software, AgWorld

• Integration with existing and development of proprietary autonomous driving systems for machinery
• Monitoring telemetry parameters of agricultural machinery to ensure compliance with standards
• Real-time visualization of machinery from different manufacturers in a unified viewer
• Predictive maintenance solutions for agriculture

• API Integration, Edge processing, Cloud-based computing, Machine learning
• Sensor fusion, path planning, positioning
• Sensor data analysis, anomaly detection

• CAN Bus (Controller Area Network), ISOBUS (ISO 11783), MQTT, Zigbee/LoRa, CANOpen, OPC UA

• OpenCV, TensorFlow, InfluxDB, Apache Kafka
• PCL, Autoware.ai, CARLA Simulator, Paho MQTT, Socket.IO
• Leaflet.js, GeoServer, QGIS

• John Deere AutoTrac
• Trimble Ag Autopilot
• Case IH AFS Connect
• Claas GPS Pilot
• AGCO Fendt VarioGuide
• New Holland IntelliSteer
• Raven Autonomy (OmniDrive)
• Kubota Tractor SmartAssist
• Topcon X25/X35
• Hexagon Agriculture’s AutoSteer