Additional menu has not been selected. Do this in the Theme Options → Header → Additional Menu.
AGERpoint

Develop a Complete Data Set for Continual Learning and Growth

OUR OBJECTIVE

Collect, produce, and enhance data sets for pesticide, pruning, and management practice trials

We collected blocks that were able to be ground navigated using our existing GroveTracker ground LiDAR. In addition, we were able to produce data sets for other blocks that were not able to be navigated on the ground with 5/10-Band Multispectral, allowing for future data fidelity with aerial Geiger Mode LiDAR (GML).

Overlay of machine learning crown detection (white point) with derived canopy location from imagery (blue outlines).

 

 

 

 

 

 

 

OUR APPROACH

Process, assemble and fuse ground and aerial data

We fused collected data with local yield and visual disease assessment data to provide our client’s Plant Scientists a full picture down to the individual tree level in AgLayers Data Science Cloud. Utilizing either GroveTracker LiDAR or a machine learning multispectral image-based method as Layer 0, we could establish a geo-rectified database of blocks and then fuse local, hand-collected yield, disease, and handheld sensor data to create Layer 0 + 1.

Blocks were scanned with a combination of terrestrial-based LiDAR or aerial-based multispectral imagery. Future collection with aerial GML LiDAR will improve fidelity.

OUR RESULTS

Scalable solutions for early disease detection and calibration for farm management practices

With the data sets for all blocks in a unified, geo-rectified location, our client’s Plant Scientists are now able to scale solutions across locations to optimize practices and results.

 

 

 

DIGITIZE
ANALYZE
COLLABORATE
1 – Digitize AGERpoint collected data:

  • GroveTracker LiDAR data
  • VitalityTracker 10-Band Multispectral aerial data
4 – Establish Geo-Rectified Blocks:

  • Established geo-rectified database using GroveTracker LiDAR layer 0
7 –Collaborate

  • Collaborate with client to produce a continually increasing and expanding dataset
2 – Insight-specific data collects:

  • Client provided yield measurements, disease assessment & hand-collected sensor data
5 – Produce Morphologies

  • Created foundation Morphology object
  • Calibrate Morphologies to LiDAR objects
SYNTHESIZE
3 – Bring Your Own Data (BYOD):

  • Local Weather Sensors
  • Soil IoT Sensors
  • Spectral Sensors
6 – Fuse Local Hand Collected Data

  • Overlay yield, disease & hand-held sensor data with layer 0 + 1
8 – Synthesize

  • Formulate in-field action plan for pruning, management and pesticide application based on overall data set and derived results

 

AGERpoint

Enhance and Augment Statistical Analysis Abilities form Unified Data Sets

OUR OBJECTIVE

Support researchers in the evaluation of citrus scions for tolerance to Citrus Greening (HLB)

In the challenge for researchers to find scions with higher tolerance to HLB, Plant Scientists not only need precise data, they need all of it. They needed assistance in compiling the various data sources and data sets into one unified place to perform statistical analysis.

 

OUR APPROACH

Digitize trees with LiDAR and aerial multispectral imagery, combined with plot map of trial design and data collected by hand from trial cooperators
Not only did we digitize GroveTracker LiDAR data, and completed an insight-specific multispectral data collect with VitalityTracker, we applied our Bring-Your-Own-Data approach to AgLayers where the client brings their own historical, current, or third-party data sets to augment the data. In this case, the client brought their trial experimental design data and observations on tree mortality.

 

We fused the data to create a Layer 0 + 1 with the trial experimental design data set which allowed the client’s Plant Scientists to perform a statistical analysis and create a variety performance data set. 

 

Scion Biomass m3
DPI-435-18A-2-31 0.47 a
Valencia 0.45 ab
RBA-26-36 0.41 abc
C4-14-53 0.37 abcd
C4-14-51 0.36 abcd
FF-1-23-130 0.35 abcde
FTP-4-13-39 0.34 abcde
Bingo 0.33 abcde
FF-1-76-52 0.33 abcde
18A-2-43 0.32 abcde
OLL-DCS-3-40 0.31 abcde
FF-1-76-51 0.31 abcde
C7-12-19 0.31 abcde
Hamlin 0.30 abcde
FTP-4-13-31 0.29 abcde
LB9-4 0.28 abcde
6-2-55 0.28 abcde
FF-1-75-113 0.27 abcde
OLL-DCS-3-36 0.26 bcde
FF-1-35-21 0.26 bcde
Tango 0.25 bcde
FF-1-75-55 0.25 bcde
FF-1-22-79 0.25 bcde
FF-1-74-52 0.25 cde
7-9-37 0.24 cde
RBA-22-29 0.24 cde
Sugarbelle 0.23 cde
FTP-1-57-105 0.22 cde
3-3-52 0.20 de
FF-1-76-50 0.19 de
FTP-6-49-96 0.19 de
FTP-4-13-7 0.15 e

 

OUR RESULTS

Unified data set with the scion type down to the individual tree + associated LiDAR and aerial data

Our client is now able to characterize the performance of varieties and their tolerance to Citrus Greening on a per plot basis. Due to the level of fused data sets, early analysis shows significant differences in scions, even though the trees are still quite small.

LiDAR point cloud of Tango scion and associated map with plant volume:

 

 

 

 

 

 

 

 

 

DIGITIZE
ANALYZE
COLLABORATE
1 – Digitize AGERpoint collected data:

  • GroveTracker LiDAR data
4 – Fuse Data:

  • Load edited complete GroveTracker LiDAR and VitalityTracker aerial data into AgLayers
  • Fuse Layer 0 + 1 with Trial Experimental Design data set
6 – Collaborate

  • Assemble field-collected data with fused measurement data set
2 – Insight-specific data collects:

  • VitalityTracker – Multispectral, (AGERpoint collect)
5 – Statistical Analysis

  • Determine variety performance data set
  • Identify, label, and statistically deal with outlier data
SYNTHESIZE
3 – Bring Your Own Data (BYOD):

  • Trial Experimental Design
  • Tree Mortality Assessments
7 – Synthesize

  • Characterize performance of varieties on per plot basis
  • (FUTURE: Per tree basis)
AGERpoint

Create a Unified Data Set with Local, Historical, and Third-Party Data

OUR OBJECTIVE

Take existing client collected local data and instrument to allow for advanced analytics 

Our client had significant amounts of locally collected data like local grove maps, site soil maps, and tree inventory, in addition to local weather, soil IoT, and spectral sensors. However, these individual data sources were not connected together in a meaningful way or down to the individual plant. They wanted to utilize their existing data to allow for advanced Plant Science analytics.


Client Provided Raw Data:

 

 

 

 

 

 

 

 

OUR APPROACH

Digitized, collected, and fused all data sets utilizing the AgLayers Data Science Cloud
Not only did we digitize our client’s existing historical data, we expanded with our own multispectral data collects and supplemented with local weather, soil IoT, and spectral sensors.

 

At this point, we established geo-rectified blocks to create a database of each individual tree asset and further analyzed by creating a foundation Morphology object. With the variety of independent data sets digitized and geo-rectified, we were able to fuse the data sets together to create meaningful views for further analysis.

 

OUR RESULTS

A unified data set that can be extended and improved with supplementary data

With this complete data set, our client’s Plant Scientists and study yield versus local farm management techniques and applied treatments to optimize performance.

Geo-Rectified Tree Asset Objects with Fused Datasets:

 

 

 

 

 

 

 

 

DIGITIZE
ANALYZE
COLLABORATE
1 – Digitize existing client provided historical data:

  • Local Grove Maps
  • Site Soil Maps
  • Tree Inventory
4 – Establish Geo-Rectified Blocks:

  • Established geo-rectified database of each tree asset
8 –Collaborate

  • Produce complete asset and tree inventory
  • Develop analytics models
2 – Insight-specific data collects:

  • VitalityTracker – Multispectral, (client collect)
5 – Produce Morphologies

  • Created foundation Morphology object
SYNTHESIZE
3 – Bring Your Own Data (BYOD):

  • Local Weather Sensors
  • Soil IoT Sensors
  • Spectral Sensors
6 – Fuse & geo-rectify data sets:

  • Fused local soil data
  • Fused by tree hand-collected yield data
  • Fused multispectral satellite data
  • Fused Soil Moisture IoT Data
Synthesize

  • Soil A has higher yield than Soil B
  • Yield by vegetative characteristic
  • Yield by soil moisture 
7 – Metrics by layer

  • Yield by Soil Type
  • Yield by vegetative characteristic
  • Yield by soil moisture 

 

AGERpoint

AGERpoint® AWARDED THREE ADDITIONAL PATENTS

Systems and Methods for Monitoring Agricultural Products and for Determining Crop Yields With High Resolution Geo-Referenced Sensors

AGERpoint®, a leading Precision Agriculture Data Analytics company centered around precise data collection and analytics, announced the issue of three additional patents by the U.S. Patent and Trademark Office. The AGERpoint patent portfolio now comprises a total of eight patents related to precision agriculture using our innovative and breakthrough technology.

The first new patent, US 10,520,482, “SYSTEMS AND METHODS FOR MONITORING AGRICULTURAL PRODUCTS” was issued on December 31st, 2019 and relates to a plant analysis system that determines spectral signatures of plants based on spectral data, and plant color based on photographic data. The spectral signatures and plant color are associated with assembled point cloud data which morphological data can be generated. A record of the plant can be created that associates the plant with the spectral signature, plant color, spectral data, assembled point cloud data, and morphological data, and stored in a library.

The second new patent, US 10,534,086, “SYSTEMS AND METHODS FOR DETERMINING CROP YIELDS WITH HIGH RESOLUTION GEO-REFERENCED SENSORS” was issued on January 14th, 2020 and relates to controlling a modular system for improved real-time yield monitoring and sensor fusion of crops in an orchard. The modular processing unit may fuse the collected data together and transmit the fused data set to a post-processing server.

The third new patent, US 10,539,545, “SYSTEMS AND METHODS FOR MONITORING AGRICULTURAL PRODUCTS” was issued January 21st, 2019 and relates to monitoring fruit production, plant growth, and plant vitality.

“We are excited to announce the expansion of our patent portfolio. We’ve spent many years innovating, including pioneering the use of Geiger Mode LiDAR and then fusing multiple data sources, to capture and uncover unique insights. We have developed the most advanced permanent crop data sensing, ML, AI and analytics platform enabled by our intellectual property.” said Andrew J. Nash, CEO of AGERpoint. He expanded with “We will continue to invest in research and development while working closely with our customers and partners as we address the data and insight needs of the scientific community to advance discovery and invention, as well as with growers and all participants in the value chain.”

AGERpoint

AGERpoint® AWARDED A NEW PATENT

Improving accuracy and timeliness of machine counting fruit

AGERpoint®, a leading Precision Agriculture Data Analytics company centered around precise data collection and analytics, announced the issue by the U.S. Patent and Trademark Office of a new, and fifth, patent on August 6, 2019 involving systems and methods for monitoring agricultural products.

The new patent, US 10,371,683, “SYSTEMS AND METHODS FOR MONITORING AGRICULTURAL PRODUCTS” relates to monitoring fruit productions, plant growth, and plant vitality. Specifically, this newest out of five patents held by AGERpoint, works to improve upon the accuracy and timeliness of machine counting of fruit on the tree or vine utilizing a data acquisition, transport, and software components.

“We are excited to continue to add to our library of patents,” said Andrew J. Nash, CEO of AGERpoint. He continued with “The ability to innovate and refine our technology sets us apart and allows us to provide extremely precise data to our partners in the value chain (food & beverage industry, growers, researchers, agronomists, insurers, industry associations, etc.).”

AGERpoint

All About Precision: AGERpoint achieves 99% accuracy in tree counting and 95% accuracy in canopy metrics

While we pride ourselves in collecting agricultural data in a timely manner (and with less manpower) than other data collection methods, our main focus is on the accuracy of the data we collect and provide to our clients. Precision is crucial to us here at AGERpoint.

We work with clients, across multiple crop types, who use the data we collect and process for a variety of business, technical, and scientific needs. This requires our data to be precise so it can provide actionable information for our clients.

How accurate can we get?
Pretty accurate – we are able to achieve a 99% accuracy in tree counting, and can achieve a 95% accuracy in canopy metrics, such as canopy diameter, volume, density, and tree height. And if we have clear visibility of trunks, we can also achieve a 95% accuracy of truck diameter.

How do we get such precise and accurate data?
Through a combination of algorithms, QAQC using custom built tools, machine learning and classification methodologies, we are able to get the accuracy as described above. And we continue to validate and calibrate our methodologies on a regular basis for the most precise results.

QAQC Edit Process

The end-to-end AGERpoint data process includes an edit function, the QAQC Edit Process, executed by our trained Geospatial engineers and utilizing proprietary and custom AGERpoint tools. These tools allow our team to manage “outlier plants” identified by the algorithms that process the raw data we collect in the field.

Our QAQC Analyst makes visual edits using our custom tools on these rare outliers, further ensuring total data accuracy. At least ~5% of all scanned trees are sampled and visually analyzed to ensure data precision.

AGERpoint identifies outliers in the data during the QAQC Edit Process.

Field Ground Truthing

As part of AGERpoint’s standard field collection processes, we have developed reference data sets based on crop types from statistically relevant samples of trees and their associated parameters (height, trunk diameter, canopy diameter, etc.). These samples are physically measured and recorded in the field. This data is makes up the ground-truth data set used to benchmark the macro results of AGERpoint’s end-to-end data process.

We compare our collected measurements against the ground-truth data sets. The collected measurement is considered correct if it falls within a threshold of distance of the ground-truth measure (typically around 10%). Comparing our measured data to these data sets it where we are able to derive our accuracy metrics.

Field ground truthing techniques of manually collecting data for comparison against our standard field collection processes to ensure accuracy.

 

 

Algorithm Benchmarking

With over 1.5 trillion data points collected across 24 different crop types, we have a large store of historical data. This allows us to compare data sets of like crop types to ensure that what is collected is consistent across the software development process and past data collections.

With our plant matching algorithms, we are able to scan the same plants again and again to further refine the accuracy for an individual client down to the individual plant level. Over time trends or issues may be easier to spot with our data collection than with previously used methods, like manual sampling.

 

Our methods together are what lead to incredibly accurate data for our clients. Are you interested in learning how you could get 99% data accuracy, with less manpower? Contact us today: Sales@AGERpoint.com

AGERpoint

NEW! AGERmetrix MorphologyExplorer

We’ve added a new feature that clients who are utilizing GroveTracker data can take advantage of – MorphologyExplorer. Point Clouds are a visualization of the thousands of data points that make up an individual tree. They show extreme levels of detail of a given tree, row, or group of trees in an easy to manipulate 3D view. Now these Point Clouds can be made available as part of AGERmetrix!

 

Previously, our Point Clouds were separate from AGERmetrix data, but with this new tool you are able to fuse the data with Point Clouds to analyze and easily identify relationships.

Select the row you would like to inspect with the Point Cloud Select Row Tool:

Row Select on AGERpoint's MorphologyExplorer

This new tool will allow customers to:

  • Look at a specific tree, row, or group of trees at an extremely detailed level
  • Provide an angle measurement tool which is valuable for researchers running pruning and other trials
  • Utilize height and width tools to measure down to the individual branch level and complete specialized measurements like stem length
  • Rotate the view to inspect and identify features or issues of a specific tree
  • Visualize trees before having to physically visit the field
  • Continually make measurements to create a total – perfect for measuring total length of branches

All of this can be done in the field on a tablet or laptop, or from the comfort of your office.

If you’re interested in seeing your Point Clouds – reach out to us today at Sales@AGERpoint.com!

Measure trunk to trunk:

Trunk to Trunk measurements on AGERpoint's MorphologyExplorer

Measure trunk to branch angle:

Angle measurements on AGERpoint's MorphologyExplorer

Measure trunk from ground to first branch:

Trunk Height measurements on AGERpoint's MorphologyExplorer

Continually measure with the Accumulation Measurement Tool for total measurements:

Measurement Accumulation on AGERpoint's MorphologyExplorer

AGERpoint

Multi-Year Trial Data On Individual Tree Level Demonstrated Positive Impact On Yield and Decreased Cost of Data Collection

“Utilizing AGERpoint®’s technology was really helpful in the data analysis. When you work with cutting edge growers, it is difficult to see with the naked eye ‘success’. AGERpoint® not only shows you the field improvements, but its verified in the final data. Proud to work with them.” – James Henderson, CEO, Prime Dirt, Inc.

CHALLENGE

GOAL TO EVALUATE CURRENT SOIL AMENDMENT TO VERIFY AND VALIDATE POSITIVE IMPACT ON YIELD.

Prime Dirt has been applying a soil amendment and rather than continue blindly, they’d like to confirm that this application has had a positive impact on yield.

In addition, they want to confirm they reducing the cost of data collection for field trials. Yield is measured on a per variety basis and is attributed down to each tree. This data collection has historically included a significant amount of man hours measuring each individual tree growth and monitoring harvest operations.

SOLUTION

COLLECTED GROVETRACKER™ DATA ANNUALLY FOR OVER THREE YEARS ON 2 BLOCKS (202 ACRES AND 76 ACRES) ON A TREE BY TREE BASIS FOR A TOTAL OF 35,592 TREES.

AGERpoint® collected data points on tree height, canopy diameter, trunk diameter, canopy volume, canopy density down to the individual tree level using GroveTracker™. YieldTracker™ data was also collected during the almond harvest season by attaching the YieldTracker™ collection system to grower supplied vehicles and collecting data at the same time the windrow was being picked up from the ground.

GroveTracker™ and YieldTracker™ data was collected and specialized agronomic services were used to process and operationalize data across 3 concurrent growing years from 2016 to 2018. Post collection, the yield data is transformed into representative volume indices and matched to a give plant and its associated row within a block. Final client data is extracted from the AGERpoint®’s SaaS service and visualized into year-over-year yield graphs and maps on a variety basis.

RESULTS

DATA COLLECTION DEMONSTRATED A 14.6% INCREASE IN YIELD AND 2.3% INCREASE IN DENSITY OF FOLIAGE BY USING PRIME DIRT PRODUCTS.

By using AGERpoint®’s products Prime Direct was able to efficiently, and effectively, show a positive increase in both yield and density of foliage by using their products.

Historically being able to collect and analyze this much data would have been extremely time consuming and costly. Because of using AGERpoint®’s products, full data sets were able to be used instead of samples – providing incredible detailed and accurate data for decision making.

AGERpoint

AGERpoint included in Seana Day’s AgTech Landscape 2019

Excited to be included in Seana Day’s, from Better Food Ventures and The Mixing Bowl, AgTech Landscape 2019 in the Field Monitoring Sensors & Solutions!

View Article on AgFunder News

AGERpoint

Reduce Labor Costs Associated With Weed Management With AGERpoint® Data And Analysis

CHALLENGE

GAIN THE ABILITY TO REDUCE LABOR ASSOCIATED WITH THE IDENTIFICATION, TRACKING, AND MANAGEMENT OF AREAS WITH WEEDS.

Our client needed a way to easily identify areas of poor weed control, while at the same time decreasing the labor associated in this management process. Historically this process has been a manual inspection on each row by farm employees – increasing time and cost.

In addition, they wanted to have the output (artifact) to be easily usable by farm workers on-site via a mobile device or tablet.

SOLUTION

COLLECTED AND COMBINED GROVETRACKER™ AND AERIAL MULTISPECTRAL IMAGERY DATA TO CRATE ONE FUSED GPS ENABLED IMAGE FOR EASY NAVIGATION OF IDENTIFIED WEED AREAS.

Taking a one-time data collect with GroveTracker™ and three rounds of aerial multispectral imagery data collected over a one-year span of time, the final product was a map showing exact locations of weeds indicted by defined markers.

The defined weed markers were then categorized by how frequently they returned allowing the identification of weeds that were tolerant to the herbicide used. This categorization allowed our client to focus eff­orts on those areas with a more advanced weed management protocol. In the past the same weed management practice would have been applied to all weeds, resulting in poor control on herbicide tolerant weeds.

RESULTS

REDUCED LABOR COST BY MORE THAN 50% DUE TO THE COLLECTION, PROCESSING, AND ANALYSIS OF BOTH GROUND AND AERIAL IMAGERY DATA.

Not only was the desired result of decreased labor costs realized, the eradication of identified weed areas aided in yield management, and reduced water requirements for aff­ected areas – furthering cost savings and revenue opportunities.