Earthworm Preference Bioassays to Evaluate Land Management Practices.

Earthworm preference tests, especially in soil-dosed exposures, can be an informative tool for assessing land management practices. Agricultural management intended to increase crop yield and improve soil sustainability includes physical manipulation of topsoil through conventional tillage, reduced or no-tillage, and/or winter cover crops. Soil amendments include the addition of inorganic nitrogen or organic nitrogen derived from soil amendments including biosolids from sewage treatment plants, poultry litter, or locally available industrial effluent. This study used 48-h Eisenia fetida preference tests to assess impacts of agricultural management practices on soil macrofauna. Although in laboratory-dosed exposures, E. fetida preferred biosolid-dosed soils (80 %-95 % recovery) over control soils, the same results were not found with field soils receiving biosolid amendments (33 % recovery). Poultry litter-amended soils (68 % recovery) were preferred over control soils. No differences were measured between tilled fields and controls, and earthworms preferred control soils over those from fields with no-tillage and cover crops. Soil assessments through laboratory exposures such as these allows science-based agricultural management decisions to maintain or improve soil health.

Detecting Intra-Field Variation in Rice Yield With Unmanned Aerial Vehicle Imagery and Deep Learning.

Unmanned aerial vehicles (UAVs) equipped with multispectral sensors offer high spatial and temporal resolution imagery for monitoring crop stress at early stages of development. Analysis of UAV-derived data with advanced machine learning models could improve real-time management in agricultural systems, but guidance for this integration is currently limited. Here we compare two deep learning-based strategies for early warning detection of crop stress, using multitemporal imagery throughout the growing season to predict field-scale yield in irrigated rice in eastern Arkansas. Both deep learning strategies showed improvements upon traditional statistical learning approaches including linear regression and gradient boosted decision trees. First, we explicitly accounted for variation across developmental stages using a 3D convolutional neural network (CNN) architecture that captures both spatial and temporal dimensions of UAV images from multiple time points throughout one growing season. 3D-CNNs achieved low prediction error on the test set, with a Root Mean Squared Error (RMSE) of 8.8% of the mean yield. For the second strategy, a 2D-CNN, we considered only spatial relationships among pixels for image features acquired during a single flyover. 2D-CNNs trained on images from a single day were most accurate when images were taken during booting stage or later, with RMSE ranging from 7.4 to 8.2% of the mean yield. A primary benefit of convolutional autoencoder-like models (based on analyses of prediction maps and feature importance) is the spatial denoising effect that corrects yield predictions for individual pixels based on the values of vegetation index and thermal features for nearby pixels. Our results highlight the promise of convolutional autoencoders for UAV-based yield prediction in rice.