Satellite Remote Sensing Shows Potential in Agricultural Monitoring

Sep 05, 2024

Paddy rice is an important agricultural product, and accurate mapping of paddy rice fields is essential for enhancing food security, promoting sustainable agriculture, increasing crop yields, and facilitating technological advancements.

A research group led by Prof. Sun Xiaobing from the Hefei Institutes of Physical Science of the Chinese Academy of Sciences developed a method for accurately mapping paddy rice cultivation in Anhui, a province in eastern China. The work is published in the journal Agriculture.

Researchers combined annual phenological features with Sentinel-1/2 imagery, leveraging satellite remote sensing and machine learning to enhance agricultural monitoring.

They derived annual phenological variations from verified ground truth data and assigned several vegetation indices to different phenological phases.

This helps them get pixel-level rice planting distribution maps through machine learning.

The research team used an automatic sample expansion technique to increase the sample size and stratified different grids within the study area.

Researchers validated the results of this method with a confusion matrix, the Anhui Statistical Yearbook, and other rice mapping algorithms of similar resolutions. The method demonstrated high accuracy in primary grain-producing areas of Anhui with less than 10% of error and showed practical value in agriculture.

Click here to see more...

Video: Seeing the Whole Season: How Continuous Crop Modeling Is Changing Breeding

Plant breeding has long been shaped by snapshots. A walk through a plot. A single set of notes. A yield check at the end of the season. But crops do not grow in moments. They change every day.

In this conversation, Gary Nijak of AerialPLOT explains how continuous crop modeling is changing the way breeders see, measure, and select plants by capturing growth, stress, and recovery across the entire season, not just at isolated points in time.

Nijak breaks down why point-in-time observations can miss critical performance signals, how repeated, season-long data collection removes the human bottleneck in breeding, and what becomes possible when every plot is treated as a living data set. He also explores how continuous modeling allows breeding programs to move beyond vague descriptors and toward measurable, repeatable insights that connect directly to on-farm outcomes.

This conversation explores:

• What continuous crop modeling is and how it works

• Why traditional field observations fall short over a full growing season

• How scale and repeated measurement change breeding decisions

• What “digital twins” of plots mean for selection and performance

• Why data, not hardware, is driving the next shift in breeding innovation As data-driven breeding moves from research into real-world programs, this discussion offers a clear look at how seeing the whole season is reshaping value for breeders, seed companies, and farmers, and why this may be only the beginning.