Andrew Crane‐Droesch
Biographic Data
| ID | 7998469 |
|---|---|
| NAME | Andrew Crane‐Droesch |
| GIVEN NAMES | Andrew |
| FAMILY NAME | Crane‐Droesch |
| SIGNATURE | DROESCH A C |
| AFFILIATIONS | University of California, Berkeley |
| VERIFIED | No |
| TOTAL WORKS | 2 |
| TOTAL CITATIONS | 0 |
| AUTHOR COUNT | 2 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2013 |
| LATEST PUBLICATION YEAR | 2018 |
| H-INDEX | 0 |
Machine learning methods for crop yield prediction and climate change impact assessment in agriculture
Crop yields are critically dependent on weather. A growing empirical literature models this relationship in order to project climate change impacts on the sector. We describe an approach to yield modeling that uses a semiparametric variant of a deep neural network, which can simultaneously account for complex nonlinear relationships in high-dimensional datasets, as well as known parametric structure and unobserved cross-sectional heterogeneity. U…
Heterogeneous global crop yield response to biochar: A meta-regression analysis
Biochar may contribute to climate change mitigation at negative cost by sequestering photosynthetically fixed carbon in soil while increasing crop yields. The magnitude of biochar's potential in this regard will depend on crop yield benefits, which have not been well-characterized across different soils and biochars. Using data from 84 studies, we employ meta-analytical, missing data, and semiparametric statistical methods to explain heterogeneit…
No prominent works on this page.
Heterogeneous global crop yield response to biochar: A meta-regression analysis
Biochar may contribute to climate change mitigation at negative cost by sequestering photosynthetically fixed carbon in soil while increasing crop yields. The magnitude of biochar's potential in this regard will depend on crop yield benefits, which have not been well-characterized across different soils and biochars. Using data from 84 studies, we employ meta-analytical, missing data, and semiparametric statistical methods to explain heterogeneit…
Machine learning methods for crop yield prediction and climate change impact assessment in agriculture
Crop yields are critically dependent on weather. A growing empirical literature models this relationship in order to project climate change impacts on the sector. We describe an approach to yield modeling that uses a semiparametric variant of a deep neural network, which can simultaneously account for complex nonlinear relationships in high-dimensional datasets, as well as known parametric structure and unobserved cross-sectional heterogeneity. U…
Agriculture (2 works) · Agronomy (2 works) · Crop yield (2 works) · Ecology (2 works) · Environmental Science (2 works) · Yield (engineering (2 works) · Agricultural engineering (1 works) · Agricultural risk and resilience (1 works) · Artificial neural network (1 works) · Biochar (1 works)