Artificial intelligence enables mobile soil analysis for sustainable agriculture

For optimizing production yield while limiting negative environmental impact, sustainable agriculture benefits greatly from real-time, on-the-spot analysis of soil at low cost. Colorimetric paper sensors are ideal candidates for cheap and rapid chemical spot testing. However, their field application requires previously unattained paper sensor reliability and automated readout and analysis by means of integrated mobile communication, artificial intelligence, and cloud computing technologies. Here, we report such a mobile chemical analysis system based on colorimetric paper sensors that operates under tropical field conditions. By mapping topsoil pH in a field with an area of 9 hectares, we have benchmarked the mobile system against precision agriculture standards following a protocol with reference analysis of compound soil samples. As compared with routine lab analysis, our mobile soil analysis system has correctly classified soil pH in 97% of cases while reducing the analysis turnaround time from days to minutes. Moreover, by performing on-the-spot analyses of individual compound sub-samples in the field, we have achieved a 9-fold increase of spatial resolution that reveals pH-variations not detectable in compound mapping mode. Our mobile system can be extended to perform multi-parameter chemical tests of soil nutrients for applications in environmental monitoring at marginal manufacturing cost. This record comprises a data set of approximately 800 images of a colorimetric paper-based chemical analysis device captured with a custom mobile application at outdoor conditions. The data set also contains three csv files collecting the color information (RGB) values and analysis results (pH values) as determined by the mobile application models from those paper-based device images. These csv files correspond to the RGB data and associated pH values as captured on the field (pre-processed), after processing post field test and a set corresponding to the measurements on a compound sample combining the 9 soil samples collected per hectare. An additional data set is included corresponding to the images and RGB data used for the calibration of the logistic regression models used by the mobile application to predict pH values from the colorimetric information. Python code is made available for the analysis of the colorimetric chemical reaction on paper of chemical reagents to soil samples across a range of acidity values, including the application of an illumination compensation method, and for the training of predictive machine learning models.