Estimating Soil Moisture with PlanetScope for Agricultural Resilience in Indonesia

Image above: PlanetScope image of rice paddies along the slopes of Mount Lawu, Indonesia taken September 17, 2022. © 2022, Planet Labs PBC. All Rights Reserved.

Along the sloping landscape of Mount Lawu in Central Java, Indonesia, farmers experience a wide variety of crop growth as a result of water availability. As rain falls onto the landscape, it is impacted by altitude and slope, moving down across highlands, middleplains, and lowlands. Some of the agricultural lands experience low soil moisture while others absorb significant amounts of rain water. This variation can make it particularly challenging for local agricultural communities to be able to predict and respond to climatic change, such as drought, which can pose a threat to crop cultivation. However, undergraduate researchers from the Sebelas Maret University in Indonesia have used PlanetScope imagery to demonstrate a possible approach to monitoring soil moisture across the highlands, middle plains, and the lowlands of the region. By extracting data from the PlanetScope imagery and determining the Color Digital Number value (obtained from RGB and infrared spectral bands), the researchers were able to run a correlation and regression analysis to determine if there was a significant difference between the actual soil moisture value (collected from site sampling and lab measurement) and the number value from the PlanetScope image. “The results showed that the accuracy of Planetscope imagery in predicting soil moisture content in the highlands, middleplains, and lowlands was 86.16%; 89.07%, and 95% [respectively]. These results indicate the high accuracy of PlanetScope images in predicting soil moisture content in rainfed rice fields,” said the authors. The researchers demonstrated an approach to estimating soil moisture along sloping landscapes at scale. “High resolution imagery such as PlanetScope can be used as an early warning of drought on agricultural land, [and] is suitable for increasing the effectiveness and monitoring of agriculture such as water management,” the authors concluded. 

The full study can be found in the IOP Conference Series: Earth and Environmental Science.