Search

Tillage practices alter soil surface structure that can be potentially captured by satellite images with both high spatial and temporal resolution. This study explored tillage practice mapping using the daily Planet Fusion surface reflectance (PF-SR) gap-free 3 m data generated by fusing PlanetScope with Landsat-8, Sentinel-2 and MODIS surface reflectance data. The study area is a 220 × 220 km2 agricultural area in South Dakota, USA, and the study used 3285 PF-SR images from September 1, 2020 to August 31, 2021. The PF-SR images for the surveyed 433 fields were sliced into 10,747 training (70%) and evaluation (30%) non-overlapping time series patches. The training and evaluation patches were from different fields for evaluation data independence. The performance of four deep learning models (i.e., 2D convolutional neural networks (CNN), 3D CNN, CNN-Long short-term memory (LSTM), and attention CNN-LSTM) in tillage practice mapping, as well as their sensitivity to different spatial (i.e., 3 m, 24 m, and 96 m) and temporal resolutions (16-day, 8-day, 4-day, 2-day and 1-day) were examined. Classification accuracy continuously increased with increases in both temporal and spatial resolutions. The optimal models (3D CNN and attention CNN-LSTM) achieved ∼77% accuracy using 2-day or daily 3 m resolution data as opposed to ∼72% accuracy using 16-day 3 m resolution data or daily 24 m resolution data. This study also analyzed the feature importance of different acquisition dates for the two optimal models. The 3D CNN model feature importances were found to agree well with the tillage practice time. High feature importance was associated with observations during the fall and spring tillage period (i.e., fresh tillage signals) whereas the crop peak growing period (i.e., tillage signals weathered and confounded by dense canopy) was characterized by a relatively low feature importance. The work provides valuable insights into the utility of deep learning for tillage mapping and change event time identification based on high resolution imagery.

ABSTRACTWe examine the interactions, decisions, and evaluations of an interdisciplinary team of researchers tasked with developing an artificial intelligence-based agricultural decision support system that can provide farmers site-specific information about managing nutrients on their land. We answer the following research questions: (1) How does a relational perspective help an interdisciplinary team conceptualize ‘responsibility' in a project that develops precision agriculture (PA)? and (2) What are some lessons for a research team embarking on a similar interdisciplinary technology development project? We show that how RI is materialized in practice within an interdisciplinary research team can produce different understandings of responsibility, notions of measurement of ‘matter,’ and metrics of success. Future interdisciplinary projects should (1) create mechanisms for project members to see how power and privilege are exercised in the design of new technology and (2) harness social sciences as a bridge between natural sciences and engineering for organic and equitable collaborations.

Artificial rain, a technology primarily used for drought relief, has recently been used for combating regional air pollution. However, there are limited available measurement data to confirm the effectiveness of this control practice. In this study, we summarize control theories and indirect but relevant observations/findings, including air pollutant reduction after natural rain events and roadside sprinkling. A brief review of artificial rain basics is also provided. Our work shows that artificial rain appears to be a promising management strategy for air pollution control. However, field measurements are needed to further assess the cost-effectiveness of the practice, as well as the other benefits or challenges it may create.